Skip to main content

Announcing StackOne Defender: leading open-source prompt injection guard for your agent • Read More →

Connect

Connectors Agent Auth MCP Connector Builder

Optimize

Tool Discovery Falcon Engine

Secure

Defender
Connectors

HRIS / HCM

Employee Onboarding Employee Offboarding

Recruiting

Application Screening Interview Scheduling

Customer Support

Ticket Triage Voice Call Summarization

Sales & CRM

Deal Risk Scoring Lead Qualification

Accounting & Finance

Invoice Processing Month-End Accruals

Marketing

Campaign Reports Lead Nurture Sequences
View all use cases

Developers

Docs Changelog Status

Learn

Blog Case Studies Events Partners
Pricing
Login Book Demo Start Free

Cohere MCP Server
for AI Agents

Production-ready Cohere MCP server with extensible actions — plus built-in authentication, security, and optimized execution.

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

Coverage

13 Agent Actions

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

MCP Actions → Create Actions →

Authentication

Agent Tool Authentication

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

Agent Auth →

Security

Agent Protection

Every Cohere 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 Cohere call.

Tools Discovery →

What is the Cohere MCP Server?

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

All Cohere MCP Tools and Actions

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

Models

  • List Models

    List available Cohere models

  • Get Model

    Get details of a specific model

Chats

  • Chat

    Generate a text response to a conversation

Embeds

  • Embed

    Generate embeddings for text inputs

Embed Jobs

  • List Embed Jobs

    List all embed jobs

Reranks

  • Rerank

    Rerank documents by relevance to a query

Datasets

  • Create Dataset

    Create a dataset by uploading a file

  • List Datasets

    List all datasets

  • Get Dataset

    Get details of a dataset

  • Delete Dataset

    Delete a dataset

Dataset Usages

  • Get Dataset Usage

    Get organization storage usage for datasets

Tokenizes

  • Tokenize

    Convert text to tokens

Detokenizes

  • Detokenize

    Convert tokens back to text

Set Up Your Cohere MCP Server in Minutes

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

MCP Clients

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>"
      ]
    }
  }
}

More AI & ML MCP Servers

OpenAI

110+ actions

Anthropic

20+ actions

Google Gemini

20+ actions

Fireflies.ai

14+ actions

All AI & ML MCP Servers →

Cohere MCP Server 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

Cohere MCP Server FAQ

Cohere MCP server vs direct API integration — what's the difference?
A Cohere MCP server and direct API integration serve different use cases. Direct API integration is for software-to-software — backend code calling Cohere. A Cohere 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 Cohere at runtime. StackOne provides both.
How does Cohere authentication work for AI agents?
Cohere 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 Cohere account; StackOne handles token exchange, storage, and refresh. Credentials never reach the LLM, and each user is isolated via origin_owner_id.
Are Cohere MCP tools vulnerable to prompt injection?
Yes — Cohere 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 Cohere agent and how do I avoid it?
Context bloat happens when Cohere tool schemas and API responses eat your Cohere agent's memory, preventing it from reasoning effectively. A single Cohere 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 Cohere agent can access?
Yes — you can limit which actions your Cohere 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 Cohere MCP server?
Yes — you can create custom agent actions for your Cohere MCP server using Connector Builder. It's an integration agent your coding assistant (Claude Code, Cursor, or Copilot) can invoke to research Cohere's API, generate production-ready connector YAML, test against the live API, and validate before you ship.
When should I NOT use a Cohere MCP server?
Skip a Cohere MCP server if your integration is purely software-to-software — direct Cohere 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 Cohere actions at runtime.
What AI frameworks and AI clients does the StackOne Cohere MCP server support?
The StackOne Cohere 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