Skip to main content

The #1 agentic semantic tool search: 91.6% first-try accuracy on S1 Search Bench • Explore Tool Discovery →

Live 61 Actions

Crelate MCP Server
for AI Agents

Connect your AI agent to StackOne's Crelate MCP server and give it 61 MCP tools out of the box. Auth, tool execution, and security all managed.

Start Free Book Demo Read Docs →
Crelate logo
Crelate MCP Server
Built by StackOne StackOne
DrataGPLocalyzeFlipMindtoolsScreenloop

Coverage

61 Agent Actions

Create, read, update, and delete across Crelate — and extend your agent's capabilities with custom actions.

MCP Actions → Build Actions →

Authentication

Agent Tool Authentication

Per-user OAuth in one call. Your Crelate MCP server gets session-scoped tokens with zero credentials stored on your infra.

Agent Auth →

Security

Agent Protection

Every Crelate tool response scanned for prompt injection in milliseconds — 88.7% accuracy, all running on CPU.

Prompt Injection Defense →

Performance

Max Agent Context. Min Cost.

Free up to 96% of your agent's context window to enhance reasoning and reduce cost, on every Crelate call.

Tools Discovery →

What is the Crelate MCP Server?

A Crelate MCP server lets AI agents read and write Crelate data through the Model Context Protocol — Anthropic's open standard for connecting LLMs to external tools. StackOne's Crelate MCP server ships with 61 pre-built actions, fully extensible via the Connector Builder — plus managed authentication, prompt injection defense, observability, and agent execution runtime. Connect it from MCP clients like Claude Desktop, Claude Code, Cursor, Goose, and VS Code, or from agent frameworks like OpenAI Agents SDK, LangChain, and Vercel AI SDK.

All Crelate MCP Tools

Every action from Crelate's API, ready for your agent. Create, read, update, and delete — scoped to exactly what you need.

Activitys

  • Create Activity

    Creates a new Activities record and returns its generated ID.

  • Get Activity

    Returns a single Activities record by its unique identifier. Returns a 404 if the record does not exist.

  • Update Activity

    Partially updates an existing Activities record. Only fields included in the request body are modified; omitted fields are left unchanged.

  • Delete Activity

    Permanently deletes an Activity record by its unique identifier.

Applications

  • List Applications

    Records must match all filters provided unless the OR filter operator is specified. <br> If no sort_by is provided, the resulting list will be sorted by ModifiedOn descending. <br> If both recent and modified_after/modified_before are provided, recent will take precedence.

  • Get Application

    Returns a single Applications record by its unique identifier. Returns a 404 if the record does not exist.

Companies

  • List Companies

    Records must match all filters provided unless the OR filter operator is specified.<br /> If no sort_by is provided, the resulting list will be sorted by ModifiedOn descending<br /> If both recent and modified_after/modified_before are provided, recent will take precedence.

  • Search Companies

    Performs a keyword search against all Company records (name, phone, address, website, or other keyword). Returned data is intentionally limited; use a more specific query or the GUID Ids with full retrieval endpoints for complete details.

Companys

  • Create Company

    Creates a new Companies record and returns its generated ID.

  • Get Company

    Returns a single Companies record by its unique identifier. Returns a 404 if the record does not exist.

  • Update Company

    Partially updates an existing Companies record. Only fields included in the request body are modified; omitted fields are left unchanged.

  • Delete Company

    Permanently deletes a Company record by its unique identifier.

Contacts

  • Create Contact

    Creates a new Contacts record and returns its generated ID.

  • List Contacts

    Records must match all filters provided unless the OR filter operator is specified. <br> If no sort_by is provided, the resulting list will be sorted by ModifiedOn descending. <br> If both recent and modified_after/modified_before are provided, recent will take precedence.

  • Get Contact

    Returns a single Contacts record by its unique identifier. Returns a 404 if the record does not exist.

  • Search Contacts

    Performs a keyword search against all Contact records (name, contact number, phone, address, website, or other keyword). Returned data is intentionally limited; use a more specific query or the GUID Ids with full retrieval endpoints for complete details.

  • Update Contact

    Partially updates an existing Contacts record. Only fields included in the request body are modified; omitted fields are left unchanged.

  • Delete Contact

    Permanently deletes a Contact record by its unique identifier.

Jobs

  • Create Job

    Creates a new Jobs record and returns its generated ID.

  • List Jobs

    Returns a paged, filterable list of job records. Supports filtering by stage, company, tags, candidates, and more.

  • Get Job

    Returns a single Jobs record by its unique identifier. Returns a 404 if the record does not exist.

  • Search Jobs

    Performs a keyword search against all Job records (name, job number, location, website, or other keyword). Returned data is intentionally limited; use a more specific query or the GUID Ids with full retrieval endpoints for complete details.

  • Update Job

    Partially updates an existing Jobs record. Only fields included in the request body are modified; omitted fields are left unchanged.

  • Delete Job

    Permanently deletes a Job record by its unique identifier.

Job Postings

  • Search Job Postings

    Search Job postings for open Jobs that are not hidden against the Job's title, description, compensation, city, state, zip, country, and company.

  • Update Job Posting

    Updates the public-facing portal posting details for a job, such as title, description, location, and compensation. Only posting-specific fields are accepted; other job fields are ignored.

Notes

  • Create Note

    Creates a new note activity on a parent record. A `ParentId` is required.

  • List Notes

    Returns a paged list of note activities. Filter by parent record, date range, or other criteria.

  • Get Note

    Returns a single note activity by its unique identifier.

  • Update Note

    Partially updates a note activity. Only fields included in the request body are modified.

  • Delete Note

    Permanently deletes a note activity by its unique identifier.

Placements

  • List Placements

    Records must match all filters provided unless the OR filter operator is specified. <br> If no sort_by is provided, the resulting list will be sorted by ModifiedOn descending. <br> If both recent and modified_after/modified_before are provided, recent will take precedence.

  • Get Placement

    Returns a single Placements record by its unique identifier. Returns a 404 if the record does not exist.

Tasks

  • Create Task

    Tasks will default to being incomplete (Completed = false) unless a value is provided.

  • List Tasks

    Returns a paged list of task activities. Filter by parent record, completion state, date range, or other criteria.

  • Get Task

    Returns a single task activity by its unique identifier.

  • Update Task

    Partially updates a task activity. Only fields included in the request body are modified.

  • Delete Task

    Permanently deletes a task activity by its unique identifier.

Other (23)

  • Create Activity With Attachment

    Creates a new Activity record and simultaneously uploads and links one or more files as Artifacts via a multipart form. Only Email Activity Types and custom Activity Types that allow attachments may be used.

  • Add Contact To Job

    Adds a single contact to the specified job's recruiting pipeline at the given workflow stage.

  • Add Contacts To Job

    Adds one or more contacts to the specified job's recruiting pipeline at the given workflow stage.

  • List Activities

    Returns a paged list of activity records. Filter by parent record, verb type, date range, or other criteria.

  • Get Activity Info

    Retrieves attribute information specific to the Activities type. This data changes rarely and Crelate recommends caching it.

  • Get Application Info

    Retrieves attribute information specific to the Applications type. This data changes rarely and Crelate recommends caching it.

  • Get Company Info

    Retrieves attribute information specific to the Companies type. This data changes rarely and Crelate recommends caching it.

  • List Companies By List

    Returns Companies records that belong to the specified saved list.

  • Get Contact Info

    Retrieves attribute information specific to the Contacts type. This data changes rarely and Crelate recommends caching it.

  • List Contacts By List

    Returns Contacts records that belong to the specified saved list.

  • Get Job Info

    Retrieves attribute information specific to the Jobs type. This data changes rarely and Crelate recommends caching it.

  • List Jobs By List

    Returns Jobs records that belong to the specified saved list.

  • Get Placement Info

    Retrieves attribute information specific to the Placements type. This data changes rarely and Crelate recommends caching it.

  • Update Job Contact Workflow Status

    This endpoint does not support handling workflow rules. Consider migrating to the [Workflow Stage](#tag/Workflow-Stages) endpoints for API-supported workflow rule interactions.

  • Remove Contact From Job

    Removes a contact from the specified job's recruiting pipeline.

  • Approve Application

    Approved applicants will be moved to the next workflow stage, typically with a meaning of "in progress".

  • Block Application

    When an applicant is blocked, they are no longer visible and any future applications from that applicant will be discarded.

  • Reject Application

    Rejected applicants will be moved to a closed negative workflow stage.

  • Apply To Job

    Submits an application to a Job and returns the created application ID. Depending on settings, applicants either route to the Recruiting Intake dashboard or auto-approve and convert to a Contact (found via the ContactId field on the Application). A resume file may be required based on Job Portal settings.

  • Change Company Status

    Available statuses can be retrieved by inspecting the results of the Companies metadata endpoint under the `EntityStatus` field.

  • Change Contact Status

    Available statuses can be retrieved by inspecting the results of the Contacts metadata endpoint under the `EntityStatus` field.

  • Disable Job Posting

    Disables the job's portal posting and removes it from any free job boards it was published to. The job record itself is not deleted.

  • Change Placement Status

    Available statuses can be retrieved by inspecting the results of the Placements metadata endpoint under the `EntityStatus` field.

Crelate AI Agent Use Cases

Connect your AI agent to Crelate and help your team scale the sales operations they run by hand today.

Post-Demo Follow-Up

Use StackOne to connect your AI agent to your CRM, email, and calendar tools to automate post-demo follow-up.

View
SalesforceHubSpotPipedriveGongFirefliesGmailMicrosoft OutlookGoogle Calendar
Deal Risk Scoring

Use StackOne to connect your AI agent to your CRM, email, and calendar tools to automate deal risk scoring and pipeline alerts.

View
SalesforceHubSpotPipedriveZoho CRMCloseFreshsalesGmailOutlook
Job Posting Distribution

Use StackOne to connect your AI agent to your ATS and job boards to automate job posting distribution.

View
GreenhouseLeverAshbySmartRecruitersWorkableJobviteiCIMSTeamtailor
More Sales & CRM use cases More Recruiting use cases

Set Up Your Crelate MCP Server in Minutes

One endpoint. Any framework. Your agent is talking to Crelate in under 10 lines of code.

MCP Clients

Claude Desktop setup guide
Claude Code setup guide
Cursor setup guide
Goose setup guide

Agent Frameworks

Claude Desktop
{
  "mcpServers": {
    "stackone": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote@latest",
        "https://api.stackone.com/mcp?x-account-id=<account_id>",
        "--header",
        "Authorization: Basic <YOUR_BASE64_TOKEN>"
      ]
    }
  }
}

Check More crm-sales MCP Servers

Capsule CRM

127+ actions

Bloomerang

104+ actions

Pipeliner CRM

59+ actions

Filevine

53+ actions

LeadDocket

26+ actions

SPS Commerce

24+ actions

All crm-sales MCP Servers →

Platform Resources

MCP Code Mode: Keeping Tool Responses Out of Agent Context

Anthropic's code_execution processes data already in context. Custom MCP code mode keeps raw tool responses in a sandbox. 14K tokens vs 500.

11 min

Comparing BM25, TF-IDF, and Hybrid Search for MCP Tool Discovery

Benchmarking BM25, TF-IDF, and hybrid search for MCP tool discovery across 916 tools. The 80/20 TF-IDF/BM25 hybrid hits 21% Top-1 accuracy in under 1ms.

10 min

Indirect Prompt Injection Defense for MCP Tools: A Technical Guide

MCP tools that read emails, CRM records, and tickets are indirect prompt injection vectors. Here's how we built a two-tier defense that scans tool results in ~11ms.

12 min

MCP vs A2A: Architecture, Security, and When to Use Each

MCP vs A2A: what each protocol standardizes, how they differ, their shared security risks including indirect prompt injection, and when to use one, both, or a hybrid architecture.

12 min

MCP vs API: What 200+ Connector Builds Taught Us

MCP wraps APIs, it doesn't replace them. After building 200+ connectors that serve both, here's when each approach wins.

14 min read

Crelate MCP Server FAQ

Does StackOne have a Crelate MCP server?
Yes. StackOne offers a hosted Crelate MCP server with 61 pre-built actions, and every action is tested and QA'd by StackOne. Connect it to Claude, Cursor, and any other MCP client, or to any agent framework through the AI Action SDK. It ships with managed agent authentication, prompt injection defense, and tool discovery with server-side execution that preserve your agent's context window and keep reasoning performance.
Crelate MCP server vs direct API integration — what's the difference?
A Crelate MCP server and direct API integration serve different use cases. Direct API integration is for software-to-software — backend code calling Crelate. A Crelate MCP server is for AI agents — MCP clients like Claude and Cursor, plus framework agents built with OpenAI, LangChain, or Vercel AI — discovering and calling Crelate at runtime. StackOne provides both.
How does Crelate authentication work for AI agents?
Crelate authentication for AI agents works through a StackOne Connect Session. Create one via the dashboard or the SDK — you get an auth link and ready-to-paste config for Claude Desktop, Cursor, and other MCP clients. Your user authenticates their own Crelate account; StackOne handles token exchange, storage, and refresh. Credentials never reach the LLM, and each user is isolated via origin_owner_id.
Are Crelate MCP tools vulnerable to prompt injection?
Yes — Crelate MCP tools can be vulnerable to indirect prompt injection. Any tool that reads user-written content — documents, messages, tickets, records, or free-text fields — is a potential vector. StackOne Defender scans every tool response before it enters the agent's context — regex patterns in ~1ms, then a MiniLM classifier in ~4ms. 88.7% accuracy, CPU-only.
What is the context bloat of a Crelate agent and how do I avoid it?
Context bloat happens when Crelate tool schemas and API responses eat your Crelate agent's memory, preventing it from reasoning effectively. A single Crelate query can return a massive JSON response, and connecting multiple tools compounds the problem. Tools Discovery and Code Mode reduce context bloat — loading only relevant tools per query and keeping raw responses out of the agent's context.
Can I limit which actions my Crelate agent can access?
Yes — you can limit which actions your Crelate agent can access directly from the StackOne dashboard. Toggle actions on or off, or restrict them to specific accounts, with no code changes to your agent. Session tokens can be scoped to exact actions so if one leaks, exposure stays contained.
Can I create custom agent actions for my Crelate MCP server?
Yes — you can create custom agent actions for your Crelate MCP server using Connector Builder. It's an integration agent your coding assistant (Claude Code, Cursor, or Copilot) can invoke to research Crelate's API, generate production-ready connector YAML, test against the live API, and validate before you ship.
When should I NOT use a Crelate MCP server?
Skip a Crelate MCP server if your integration is purely software-to-software — direct Crelate API integration is simpler when no AI agent is involved. For deterministic, compliance-critical operations (financial transactions, regulatory reporting), direct API gives you predictable behavior without agent-driven decision-making. MCP shines when AI agents need to dynamically discover and call Crelate actions at runtime.
What AI frameworks and AI clients does the StackOne Crelate MCP server support?
The StackOne Crelate MCP server supports both. MCP clients (paste-and-go apps): Claude Desktop, Claude Code, Cursor, VS Code, Goose. Agent frameworks (code SDKs you build with): OpenAI Agents SDK, Anthropic, Vercel AI, Google ADK, CrewAI, Pydantic AI, LangChain, LangGraph, Azure AI Foundry.

Put your AI agents to work

All the tools you need to build and scale AI agent integrations, with best-in-class connectivity, execution, and security.

Start Free Book Demo