Enables AI agents to read, search, and send emails through the Model Context Protocol using standard IMAP (receiving) and SMTP (sending) protocols. Compatible with any email provider that supports these protocols: corporate mail servers, Tencent Enterprise Mail, Alibaba Enterprise Mail, Zoho, Microsoft Exchange/Office 365, Gmail (via app password), 163, QQ, and more. Agents can search messages, read attachments, send formatted emails, and reply to threads — all without provider-specific OAuth setup.

让智能体通过 MCP 使用标准 IMAP（收信）和 SMTP（发信）协议读取、搜索和发送邮件。兼容支持这些协议的任意邮件服务商：企业邮件服务器、腾讯企业邮、阿里企业邮、Zoho、Microsoft Exchange/Office 365、Gmail（应用专用密码）、163、QQ 等。智能体可以搜索邮件、读取附件、发送格式化邮件和回复邮件，无需针对服务商配置 OAuth。

通过标准 IMAP 和 SMTP 收发邮件，适用于任意邮件服务商。

Connect to IMAP when needed, actively verify SMTP, then return structured status for both services.

check_connection

Find the newest sent message with the same normalized subject, optionally narrowed by recipient and date, then continue its thread. Designed for recurring reports; reply-all and quoted history both default to true.

continue_email_thread

Permanently delete one existing mailbox-scoped message using targeted UID EXPUNGE. Fails safely when the UID is missing or the IMAP server lacks UIDPLUS, and returns a structured unknown outcome when a transport failure prevents confirmation.

delete_message

Find messages from a sender that have no thread-header reply in the sent mailbox. Messages without Message-ID are returned separately as unknown.

find_unreplied_messages

Retrieve one message, including full bodies and attachment metadata. Set markSeen only when the message should be marked as read.

get_message

Retrieve multiple messages from one mailbox, including full bodies and attachment metadata. Fails if any requested UID is missing or the aggregate response-body budget would be exceeded.

get_messages

List all available mailboxes (folders). Auto-connects to IMAP when needed.

list_mailboxes

Move an existing mailbox-scoped message to another existing mailbox. If a move, copy, or source-cleanup outcome cannot be confirmed, returns a structured partial error that must be inspected before retrying.

move_message

Reply to a mailbox-scoped message with threading headers, optional reply-all recipients, signature, and quoted original content.

reply_to_email

Save one or all attachments from a mailbox-scoped message into an allowed local directory. If a later write fails, returns the files already saved as a structured partial result.

save_attachment

Search one or more mailboxes with combined filters. Defaults to INBOX and the detected sent mailbox. Returns message summaries unless includeBody is true; full-body hydration fails explicitly if a selected message disappears or the aggregate response-body budget would be exceeded.

search_messages

Send a new email via SMTP and try to save a MIME-equivalent copy with the accepted Message-ID to the sent mailbox.

send_email

Read and send email over standard IMAP and SMTP with any email provider.

com.forgeuno/email-mcp

Email account username, usually the email address

EMAIL_USER

EMAIL_PASS

IMAP server host, for example imap.gmail.com

IMAP_HOST

IMAP_PORT

IMAP over implicit TLS; this version does not support other modes

IMAP_SECURE

SMTP server host, for example smtp.gmail.com

SMTP_HOST

SMTP port (465 for implicit TLS, 587 for STARTTLS)

SMTP_PORT

Use implicit TLS (true, port 465); false requires STARTTLS (port 587)

SMTP_SECURE

Email (IMAP + SMTP)

Enables AI agents to scrape and crawl websites through the Model Context Protocol using Firecrawl. Converts web pages into clean, LLM-friendly markdown format, handling JavaScript rendering, pagination, and anti-bot measures. Ideal for extracting structured content from websites at scale.

让智能体通过 MCP 使用 Firecrawl 抓取和爬取网站，把网页转换为干净、适合大模型处理的 Markdown，并处理 JavaScript 渲染、分页和反爬措施，适合大规模提取网站的结构化内容。

通过 Firecrawl 抓取、爬取和搜索网页，并转换为干净的 Markdown。


Run web research that returns structured data when the URLs are not known or the answer spans several sites. Describe the fields you need in `prompt`, optionally pass a JSON `schema` and seed `urls`, and the research agent searches, navigates, reads pages, and returns JSON assembled across sources. Use it to research an entity plus its fields (founders, pricing, contact details), to build lists and datasets (companies, people, products, jobs, papers), and for pages that need navigation or interaction to reach the data. Optional `effort` sets the reasoning budget, `maxCredits` caps spend, and `strictConstrainToURLs` keeps the agent to the supplied `urls`.

This call returns only a job ID, not the research result. Read the job with `firecrawl_agent_status` until it reaches `completed` or `failed`; a typical research run takes one to three minutes. For one known URL use `firecrawl_scrape` (with formats: ["json"] for structured output); for a plain lookup that a results page answers, use `firecrawl_search`.

The job also returns a `threadId`. To continue that thread, pass it with a follow-up `prompt`; omitted `mode`, `urls`, `schema` and exchange settings carry over from the previous turn.

The agent only calls Alexandria providers whose terms the team has accepted. `exchange.skippedProviders` lists gated providers. With `exchange.onTermsRequired` "ask", a terms `pendingApproval` and `exchange.requiresAction` carry the `approvalId` and provider requirements. Read terms/show through `firecrawl_scrape`. An organization admin must accept terms in the Firecrawl dashboard at the provider URL or https://www.firecrawl.dev/app/settings?tab=data-sources. Ignore any terms/accept call in the API response. Only after the admin confirms acceptance, resume with the same `threadId` and `exchange.approve: {approvalId}`; this does not accept terms. To decline, use `exchange.decline: {approvalId}`. Never infer acceptance from a data request.


firecrawl_agent


Retrieve progress or final results for a `firecrawl_agent` job ID. A `processing` response is non-terminal and does not contain the final research result. Check again after 15–30 seconds until the status is `completed` or `failed`; a typical research run takes one to three minutes and complex jobs can take longer. If the job cannot finish within the task's available time, use `firecrawl_search` and `firecrawl_scrape` to complete the requested output.

Returns job status, progress information, and result data when completed.


firecrawl_agent_status


Retrieve the current status, progress, and available results for an existing crawl ID. This only reads Firecrawl job state and does not start or modify the crawl.


firecrawl_check_crawl_status


Start a multi-page crawl at a website URL, poll it to a terminal state, and return the final status and collected data. Scope can be bounded with include/exclude paths, depth, page limit, subdomain/external-link controls, sitemap handling, delay, and scrape options.

Crawl results can be large; use conservative limits when full-site coverage is unnecessary. Webhooks and interactive scrape actions are unavailable in safe mode. Returns the crawl ID, status, and page data.


firecrawl_crawl


Get the authenticated Firecrawl team's current credit balance or historical credit consumption. Use the current view to answer how many credits remain or to check billing-period boundaries. Use the historical view for monthly usage reporting and trend analysis.

The current view returns `remainingCredits`, `planCredits`, `billingPeriodStart`, and `billingPeriodEnd`. Extra purchased or granted credits can make `remainingCredits` greater than `planCredits`. Billing-period dates may be null when the upstream billing provider has no period metadata.

The historical view returns periods sorted by start date with `startDate`, `endDate`, and `creditsUsed`. Set `byApiKey` to include separate periods per API key, identified by the optional `apiKey` field. The newest period's `endDate` can be null.


firecrawl_credit_usage


Search an index of public repositories, GitHub issues, merged pull requests, repository READMEs, and code documentation for programming questions that need external documentation or upstream evidence.

Returns ranked results with an ID, source type, URL, title, and the matched passages in markdown.


firecrawl_developer_search

Browse Alexandria data providers and workflows or read a selected contract. Alexandria covers companies, people, jobs, finance and filings, public records and government spending, real estate, places and restaurants, retail and prices, package registries and developer data, news, research, and more: typed, sourced records through published contracts. Prefer normal firecrawl_search for a data task; it already returns matching providers. Use this tool when the contract you need was not returned in full, to browse a category when search found nothing, or before scraping the same fields from several pages. Discovery is free. Use query for semantic discovery or urls to find providers for a website. With no arguments, browse categories, then providers and tools. Contracts describe the inputs and outputs for execution through firecrawl_scrape. nextTool identifies further discovery or pagination. Discovery does not execute providers. Use firecrawl_search when you also need web results.

firecrawl_find_tools


Search US federal, state, and local statutes, regulations, codes, court opinions, and other government publications for legal or regulatory questions that need primary text. Clarify a missing jurisdiction or ambiguous as-of date before identifying the governing rule.

Returns ranked results with a position, title, URL, and matched snippet. Results may include historical versions, bill text, agency guidance, and third-party reproductions. Verify the issuer, jurisdiction, enacted/effective status, and version before citing current governing law. Read a known URL or additional page context with firecrawl_scrape. Use general search for non-US questions or missing coverage; no hits does not establish that no applicable law exists.


firecrawl_gov_search


Open or reuse a live browser session to navigate a page, click controls, fill fields, or run browser code. Provide either `url` or `scrapeId`, and either a natural-language `prompt` or executable `code`; code can run as Bash, Python, or Node with a bounded timeout.

This acts on the live site, so actions such as form submission can create persistent external side effects. Returns execution output, stdout/stderr, exit status, and session viewing URLs.


firecrawl_interact


Stop the live interact session associated with a `scrapeId` and release its resources. Returns a success confirmation.


firecrawl_interact_stop


Enumerate URLs indexed under one website through Firecrawl without fetching each page's content. Use this when the request asks for a site's URL inventory, when several relevant pages must be located, or when the desired page URL is unknown. An optional `search` term narrows the URL list, while sitemap, subdomain, query-parameter, and result-limit options control coverage.

Returns matching URLs rather than page bodies. Retrieve one page with `firecrawl_scrape`; collect content across multiple pages with `firecrawl_crawl`. Authenticated responses can include an `id` for optional map feedback.


firecrawl_map


Retrieve one monitor check and its page-level results, optionally filtered by page status. Pages report `same`, `new`, `changed`, `removed`, or `error`; configured goal judging can add a meaningful-change decision.

Markdown tracking returns a unified text diff, JSON tracking returns field paths with previous/current values and a current snapshot, and mixed tracking returns both. Returns one page of results plus a `next` URL when more pages exist.


firecrawl_monitor_check


List historical checks for a monitor, optionally filtered by status and bounded by a result limit. Returns one page of check summaries and pagination metadata.


firecrawl_monitor_checks


Create a recurring scrape, crawl, or search monitor that compares each check with its retained predecessor. The simple form accepts `page`/`pages` or `queries` plus a plain-language `goal`; the advanced `body` form controls targets, schedule, change-tracking formats, judging, retention, webhook, and notifications.

In the simple form, a `goal` is required. If `queries` contains one or more non-empty values and is supplied with `page`/`pages`, `queries` create the search target and page targets are ignored. A monitor schedules future network checks and can send configured email or webhook notifications. Returns the created monitor.


firecrawl_monitor_create


Permanently delete a monitor by ID and stop its future schedule. This operation cannot be undone and returns deletion status.


firecrawl_monitor_delete


Retrieve one monitor by ID, including its configuration and current state. This does not run or modify the monitor.


firecrawl_monitor_get


List monitors for the authenticated account with optional pagination controls. Returns one page of monitor records and pagination metadata.


firecrawl_monitor_list


Queue an immediate check for a monitor outside its normal schedule. This starts network work for the monitor's configured targets and returns the queued check.


firecrawl_monitor_run


Patch an existing monitor by ID. The body can change its name, active/paused status, schedule, targets, goal, judging, webhook, notifications, or retention; these changes affect future scheduled checks.

Returns the updated monitor.


firecrawl_monitor_update


Parse one supported document into markdown, HTML, links, summary, targeted answers, or JSON matching a schema. Supported inputs include common HTML, PDF, Word, RTF, OpenDocument, and spreadsheet files; PDF parsing can be bounded with `pdfOptions.maxPages`.

Local MCP reads `filePath` from the server filesystem. Hosted MCP uses two calls: first provide `filePath` to receive upload instructions, upload locally, then call again with the returned `uploadRef`; do not send both fields together. Remote web URLs belong in `firecrawl_scrape`.

Set `redactPII` to request redaction of personally identifiable information in the returned content. `zeroDataRetention` requires an eligible authenticated account; omit it for anonymous keyless use. Returns upload instructions for hosted phase one or parsed document content for the final call. Authenticated final responses can include a `data.metadata.scrapeId` for optional parse feedback.


firecrawl_parse


Retrieve canonical metadata for one paper ID, such as an arXiv, PMC, PMID, or DOI identifier. Returns the title, abstract, authors, categories, source IDs, and dates as markdown.


firecrawl_research_inspect_paper


Retrieve in-body passages from one paper that are relevant to a specific question. Full text is available only for indexed papers; `k` controls the number of passages.

Returns matching passages or a notice when full text is unavailable.


firecrawl_research_read_paper


Find citation-graph candidates from one to ten `seed_ids`; the first ID is the primary seed and later IDs are anchors. `mode` defaults to `similar` (co-citation/bibliographic coupling); `citers` returns papers citing a seed and `references` papers cited by a seed. `intent` ranks candidates.

Returns ranked candidates and the evaluated pool size.


firecrawl_research_related_papers


Search paper metadata and abstracts with a natural-language query across the indexed corpus, which spans biomedical, life-science, and clinical literature (PubMed, bioRxiv, medRxiv) alongside arXiv and other scientific sources. Optional author, category, and date filters constrain results.

Several distinct framings of the same question surface different papers than a single query does.

Returns ranked papers with canonical IDs, titles, authors, and abstracts.


firecrawl_research_search_papers


Scrape one URL and return its content: markdown by default, or HTML, links, screenshots, branding data, a targeted answer, or JSON matching a supplied schema. Use it when the request identifies a page and needs its content or defined fields: the user gives a URL or names a page or PDF and wants it read or summarized, or wants prices, specs, contact details or a table from it. Use `firecrawl_search` when additional web sources are needed; on an authenticated session, `firecrawl_map` lists a site's URLs and `firecrawl_crawl` collects a set of pages.

Firecrawl may serve recently indexed content; set `maxAge: 0` for a live fetch or a smaller `maxAge` to bound staleness. A successful response does not by itself confirm the page is still current. Browser actions can change the live page when interactive actions are enabled. Authenticated responses can include a `metadata.scrapeId` for optional scrape feedback.

`firecrawl_search` and `firecrawl_find_tools` can discover providers for the same fields across several pages; a matching provider returns typed records in one call.

With `alexandria` in place of `url`, the tool runs catalogued provider capabilities instead of fetching a page. Provider discovery and execution require an API key on a team with Alexandria enabled.


firecrawl_scrape


Search web, news, or image sources and return ranked results with query-relevant highlights. Use it for current information, or to list businesses, people, products, jobs or events with websites, prices or contacts. Each web result is a title, URL, and description; use `firecrawl_scrape` on a result URL when the excerpt is not enough.

Authenticated search also returns matching Alexandria data providers in data.tools (companies, people, jobs, finance and filings, public records and government spending, real estate, places and restaurants, retail and prices, package registries and developer data, news, research, and more). Prefer a provider over scraping pages when the task needs the same fields across several entities, exact figures or timestamps, provenance, or many records; use web results when they already answer the question. Authenticated searches always add alexandria to the sources, so sources: ["web"] also returns providers; domainTools: false turns off website-matched tools only.

On an authenticated session, tool matches describe available capabilities; `firecrawl_find_tools` returns their contracts and `firecrawl_scrape` with an `alexandria` body executes a selected capability. Keyless sessions get no Alexandria matches in data.tools.

For a programming question, add `categories: ["developer"]`; its hits return in `data.web` with `category: "developer"`. For a legal or regulatory question, `categories: ["gov"]` returns hits in `data.web` with `category: "gov"` and cannot be combined with other categories; authenticated sessions also have `firecrawl_gov_search` as the dedicated tool. Verify gov results' issuer, jurisdiction, status, and version before citing current law. `categories: ["research"]` restricts web results to research-affiliated websites; the `firecrawl_research_*` tools are a separate surface over paper abstracts and full text (PubMed, bioRxiv, medRxiv, arXiv). Returns source-type result groups and usage metadata. Authenticated responses can include an `id` for optional search feedback.


firecrawl_search

Web scraping, crawling and search that turns pages into clean markdown via Firecrawl.

io.github.firecrawl/firecrawl-mcp-server

FIRECRAWL_API_KEY

Firecrawl

Enables AI agents to read and update HubSpot CRM data through the Model Context Protocol. Supports contact and company lookup, deal pipeline management, ticket creation, and note logging. Ideal for sales automation, lead enrichment, and customer support workflows that use HubSpot as the system of record.

让智能体通过 MCP 读取和更新 HubSpot CRM 数据：查询联系人和公司、管理交易管道、创建工单和记录备注。适合以 HubSpot 为业务数据中心的销售自动化、线索补全和客户支持工作流。

读取和更新 HubSpot CRM 中的联系人、公司、交易和工单。


    🛡️ Guardrails:
      1.  Data Modification Warning: This tool modifies HubSpot data. Only use when the user has explicitly requested to update their CRM.

    🎯 Purpose:
      1. Establishes relationships between HubSpot objects, linking records across different object types, by creating associations between objects in batch.
      2. Uses a single set of association types for all associations in the batch.

    📋 Prerequisites:
      1. Use the hubspot-get-user-details tool to get the OwnerId and UserId if you don't have that already.
      2. Use the hubspot-get-association-definitions tool to identify valid association types before creating associations.
  

hubspot-batch-create-associations


    🛡️ Guardrails:
      1. Data Modification Warning: This tool modifies HubSpot data. Only use when the user has explicitly requested to update their CRM.

    🎯 Purpose:
      1. Creates multiple HubSpot objects of the same objectType in a single API call, optimizing for bulk operations.

    📋 Prerequisites:
      1. Use the hubspot-get-user-details tool to get the OwnerId and UserId if you don't have that already.
      2. Use the hubspot-list-objects tool to sample existing objects for the object type.
      3. Use the hubspot-get-association-definitions tool to identify valid association types before creating associations.
  

hubspot-batch-create-objects


    🎯 Purpose:
      1. Retrieves multiple HubSpot objects of the same object type by their IDs in a single batch operation.

    🧭 Usage Guidance:
      1. Use this tool to retrieve objects when the object IDs are known.
  

hubspot-batch-read-objects


    🛡️ Guardrails:
      1. Data Modification Warning: This tool modifies HubSpot data. Only use when the user has explicitly requested to update their CRM.

    🎯 Purpose:
      1. Updates multiple existing HubSpot objects of the same objectType in a single API call.
      2. Use this tool when the user wants to update one or more existing CRM objects.
      3. If you are unsure about the property type to update, identify existing properties of the object and ask the user.

    📋 Prerequisites:
      1. Use the hubspot-get-user-details tool to get the OwnerId and UserId if you don't have that already.
      2. Use the hubspot-list-objects tool to sample existing objects for the object type.
      3. If hubspot-list-objects tool's response isn't helpful, use hubspot-list-properties tool.
  

hubspot-batch-update-objects


    🛡️ Guardrails:
      1. Data Modification Warning: This tool modifies HubSpot data. Only use when the user has explicitly requested to update their CRM.

    🎯 Purpose:
      1. Creates a HubSpot engagement (Note or Task) associated with contacts, companies, deals, or tickets.
      2. This endpoint is useful for keeping your CRM records up-to-date on any interactions that take place outside of HubSpot.
      3. Activity reporting in the CRM also feeds off of this data.

    📋 Prerequisites:
      1. Use the hubspot-get-user-details tool to get the OwnerId and UserId.

    🧭 Usage Guidance:
      1. Use NOTE type for adding notes to records
      2. Use TASK type for creating tasks with subject, status, and assignment
      3. Both require relevant associations to connect them to CRM records
      4. Other types of engagements (EMAIL, CALL, MEETING) are NOT supported yet.
      5. HubSpot notes and task descriptions support HTML formatting. However headings (<h1>, <h2>, etc.) look ugly in the CRM. So use them sparingly.
  

hubspot-create-engagement


    🛡️ Guardrails:
      1. Data Modification Warning: This tool modifies HubSpot data. Only use when the user has explicitly requested to update their CRM.

    🎯 Purpose:
      1. Creates new custom properties for HubSpot object types, enabling data structure customization.

    📋 Prerequisites:
      1. Use the hubspot-get-user-details tool to get the OwnerId and UserId if you don't have that already.
      2. Use the hubspot-list-objects tool to sample existing objects for the object type.
      3. If hubspot-list-objects tool's response isn't helpful, use hubspot-list-properties tool.

    🧭 Usage Guidance:
      1. Use this tool when you need to create a new custom property for a HubSpot object type.
      2. Makes sure that the user is looking to create a new property, and not create an object of a specific object type.
      3. Use list-properties to get a list of all properties for a given object type to be sure that the property does not already exist.
      4. Use list-properties to to understand the data structure of object properties first.
  

hubspot-create-property


    🎯 Purpose:
      1. Use this tool when the user wants to submit feedback about HubSpot MCP tool.
      2. Use this tool proactively when the other HubSpot MCP tools are unable to solve the user's tasks effectively.
      3. Use this tool when you sense dissatisfaction from the user using HubSpot MCP tools.
      4. Feedback will help us improve the HubSpot MCP tools in future iterations.
  

hubspot-generate-feedback-link


    🎯 Purpose:
      1. Retrieves valid association types between specific HubSpot object types.

    📦 Returns:
      1. Array of valid association definitions with type IDs, labels, and categories.

    🧭 Usage Guidance:
      1. Always use before creating associations to ensure valid relationship types or to help troubleshoot association creation errors.
  

hubspot-get-association-definitions


    🎯 Purpose:
      1. Retrieves a HubSpot engagement by ID.
  

hubspot-get-engagement


    🎯 Purpose:
      1. Generates HubSpot UI links for different pages based on object types and IDs.
      2. Supports both index pages (lists of objects) and record pages (specific object details).

    📋 Prerequisites:
      1. Use the hubspot-get-user-details tool to get the PortalId and UiDomain.

    🧭 Usage Guidance:
      1. Use to generate links to HubSpot UI pages when users need to reference specific HubSpot records.
      2. Validates that object type IDs exist in the HubSpot system.
  

hubspot-get-link


    🎯 Purpose:
      1. This tool retrieves detailed information about a specific property for a HubSpot object type.
      2. You can use this to get all metadata related to a property, including its type, options,
         and other configuration details.
  

hubspot-get-property


    🎯 Purpose:
      1. Retrieves all custom object schemas defined in the HubSpot account.

    🧭 Usage Guidance:
      1. Before working with custom objects to understand available object types,
         their properties, and associations.

    📦 Returns:
      1. Provides the objectTypeId and objectType for each schema.
      2. These attributes should be used for this object type instead of "custom" in subsequent requests.
  

hubspot-get-schemas


    🎯 Purpose
      1. Authenticates and analyzes the current HubSpot access token, providing context about the user's permissions and account details.

    🧭 Usage Guidance:
      1. This tool must be used before performing any operations with Hubspot tools to determine the identity of the user, and permissions they have on their Hubspot account.

    📦 Returns:
      1. User ID, Hub ID, App ID, token type, a comprehensive list of authorized API scopes, and detailed owner information, and account information.
      2. The uiDomain and hubId can be used to construct URLs to the HubSpot UI for the user.
      3. If the user is an owner, the ownerId will help identify objects that are owned by the user.
  

hubspot-get-user-details


    🎯 Purpose:
      1. This tool retrieves detailed information about a specific workflow from the HubSpot account.

    🧭 Usage Guidance:
      1. Use the "flowId" parameter to specify which workflow to retrieve.
      2. This endpoint returns complete workflow information including actions, enrollment criteria, and scheduling.
      3. Use the hubspot-list-workflows tool first to identify the workflow ID you need.
  

hubspot-get-workflow


    🎯 Purpose:
      1. Retrieves existing relationships between a specific object and other objects of a particular type.
      2. For example, you can find all companies that a contact is associated with, all deals related to a company, or discover which customers have an open ticket.

    📦 Returns:
      1. Collection of associated object IDs and relationship metadata.
      2. Use hubspot-batch-read-objects to get more information about the associated objects.

    🧭 Usage Guidance:
      1. Use this tool when mapping relationships between different HubSpot objects to understand your data's connections.
      2. This tool is ideal when you already know a specific record's ID and need to discover its relationships with other object types.
      3. Prefer this over hubspot-search-objects tool when exploring established connections rather than filtering by properties or criteria.
  

hubspot-list-associations


    🎯 Purpose:
      1. Retrieves a paginated list of objects of a specified type from HubSpot.

    📦 Returns:
      1. Collection of objects with their properties and metadata, plus pagination information.

    🧭 Usage Guidance:
      1. Use for initial data exploration to understand the data structure of a HubSpot object type.
      2. Helps list objects when the search criteria or filter criteria is not clear.
      3. Use hubspot-search-objects for targeted queries when the data structure is known.
      4. Use hubspot-batch-read-objects to retrieve specific objects by their IDs.
      5. Use hubspot-list-associations to list associations between objects.
  

hubspot-list-objects


    🎯 Purpose:
      1. This tool retrieves a complete catalog of properties for any HubSpot object type.

    🧭 Usage Guidance:
      1. This API has a large response that can consume a lot of tokens. Use the hubspot-list-objects tool to sample existing objects for the object type first.
      2. Try to use the hubspot-get-property tool to get a specific property.
      3. Use at the beginning of workflows to understand available data structures.
  

hubspot-list-properties


    🎯 Purpose:
      1. This tool retrieves a paginated list of workflows from the HubSpot account.

    🧭 Usage Guidance:
      1. Use the "limit" parameter to control the number of results returned per page.
      2. For pagination, use the "after" parameter with the value from the previous response's paging.next.after.
      3. This endpoint returns essential workflow information including ID, name, type, and status.
  

hubspot-list-workflows


    🎯 Purpose:
      1. Performs advanced filtered searches across HubSpot object types using complex criteria.

    📋 Prerequisites:
      1. Use the hubspot-list-objects tool to sample existing objects for the object type.
      2. If hubspot-list-objects tool's response isn't helpful, use hubspot-list-properties tool.

    📦 Returns:
      1. Filtered collection matching specific criteria with pagination information.

    🧭 Usage Guidance:
      1. Preferred for targeted data retrieval when exact filtering criteria are known. Supports complex boolean logic through filter groups.
      2. Use hubspot-list-objects when filter criteria is not specified or clear or when a search fails.
      3. Use hubspot-batch-read-objects to retrieve specific objects by their IDs.
      4. Use hubspot-list-associations to get the associations between objects.

    🔍 Filtering Capabilities:
      1. Think of "filterGroups" as separate search conditions that you want to combine with OR logic (meaning ANY of them can match).
      2. If you want to find things that match ALL of several conditions (AND logic), put those conditions together in the same filters list.
      3. If you want to find things that match AT LEAST ONE of several conditions (OR logic), put each condition in a separate filterGroup.
      4. You can include a maximum of five filterGroups with up to 6 filters in each group, with a maximum of 18 filters in total.
  

hubspot-search-objects


    🛡️ Guardrails:
      1. Data Modification Warning: This tool modifies HubSpot data. Only use when the user has explicitly requested to update their CRM.

    🎯 Purpose:
      1. Updates an existing HubSpot engagement (Note or Task).
      2. Allows modification of engagement attributes, content, and metadata.

    📋 Prerequisites:
      1. You need the engagement ID to update an existing engagement.
      2. Use the hubspot-get-engagement tool to get the current engagement details if needed.
      3. Use the hubspot-get-user-details tool to get the owner ID.

    🧭 Usage Guidance:
      1. Use for updating NOTE content or TASK details (subject, description, status).
      2. Only include the fields you want to update - other fields will remain unchanged.
      3. HubSpot notes and task descriptions support HTML formatting. However headings (<h1>, <h2>, etc.) look ugly in the CRM. So use them sparingly.
  

hubspot-update-engagement


    🛡️ Guardrails:
      1. Data Modification Warning: This tool modifies HubSpot data. Only use when the user has explicitly requested to update their CRM.

    🎯 Purpose:
      1. Updates existing custom properties for HubSpot object types, enabling data structure customization.

    🧭 Usage Guidance:
      1. Use hubspot-list-objects tool to sample existing objects for the object type.
      2. If hubspot-list-objects tool's response isn't helpful, use hubspot-list-properties tool.
  

hubspot-update-property

Read and update HubSpot CRM contacts, companies, deals and tickets.

com.forgeuno/hubspot-mcp

PRIVATE_APP_ACCESS_TOKEN

HubSpot

Enables AI agents to interact with Notion workspaces through the Model Context Protocol. Supports reading and creating pages, querying databases, managing blocks, and searching content. Access is scoped by the Notion integration permissions configured by the workspace admin.

让智能体通过 MCP 操作 Notion 工作区：读取和创建页面、查询数据库、管理块以及搜索内容。访问范围受工作区管理员为 Notion 集成配置的权限限制。

通过 Notion API 读写 Notion 页面、数据库和块。

Notion | Create comment
Error Responses:
400: Bad request

API-create-a-comment

Notion | Create a data source
Error Responses:
400: Bad request

API-create-a-data-source

Notion | Delete a block
Error Responses:
400: Bad request

API-delete-a-block

Notion | Retrieve block children
Error Responses:
400: Bad request

API-get-block-children

Notion | Retrieve your token's bot user
Error Responses:
400: Bad request

API-get-self

Notion | Retrieve a user
Error Responses:
400: 400

API-get-user

Notion | List all users
Error Responses:
400: 400

API-get-users

Notion | List templates in a data source
Error Responses:
400: Bad request

API-list-data-source-templates

Notion | Move a page
Error Responses:
400: Bad request

API-move-page

Notion | Append block children
Error Responses:
400: Bad request

API-patch-block-children

Notion | Update page properties
Error Responses:
400: Bad request

API-patch-page

Notion | Create a page
Error Responses:
400: Bad request

API-post-page

Notion | Search by title
Error Responses:
400: Bad request

API-post-search

Notion | Query a data source
Error Responses:
400: Bad request

API-query-data-source

Notion | Retrieve a block
Error Responses:
400: Bad request

API-retrieve-a-block

Notion | Retrieve comments
Error Responses:
400: Bad request

API-retrieve-a-comment

Notion | Retrieve a data source
Error Responses:
400: Bad request

API-retrieve-a-data-source

Notion | Retrieve a database
Error Responses:
400: Bad request

API-retrieve-a-database

Notion | Retrieve a page
Error Responses:
400: Bad request

API-retrieve-a-page

Notion | Retrieve a page property item
Error Responses:
400: Bad request

API-retrieve-a-page-property

Notion | Retrieve a page as Markdown
Error Responses:
400: Bad request
403: The integration lacks the read/update content capability required for this page.
404: Page not found or not shared with the integration.
429: Rate limited.

mcp servers

communication (1)

Email (IMAP + SMTP) restricted

content (1)

Firecrawl caution

productivity (2)

HubSpot caution

Notion caution

search (3)

Context7 safe

Exa Search safe

Tavily Search safe