cohere-mcp
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@cohere-mcpChat with Cohere about machine learning"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Cohere MCP Server
A Type 3 DAuth MCP server for Cohere AI API. Provides chat, embeddings, reranking, classification, and summarization using Cohere's AI models.
Features
Chat — Conversational AI similar to chat completions
Embed — Text embeddings with multiple input types
Rerank — Rerank documents by relevance
Classify — Classify text into categories
Summarize — Text summarization
List Models — View available Cohere models
Related MCP server: litellm-mcp
Authentication
This server uses Type 3 DAuth (Dedalus Auth) — your API key is encrypted client-side and decrypted in a secure Dedalus enclave.
Get Your Cohere API Key
Go to https://cohere.ai/AI-API
Sign up and get an API key
Copy the key
Installation
git clone https://github.com/dedalus-labs/cohere-mcp.git
cd cohere-mcp
pip install -e .
cp .env.example .env
# Edit .env and add COHERE_API_KEYAvailable Tools
cohere_chat
Chat with Cohere AI.
cohere_chat(
message="Hello!",
model="command",
temperature=0.7,
max_tokens=500,
)cohere_embed
Generate text embeddings.
cohere_embed(
texts=["Hello world", "This is a test"],
model="embed-english-v3.0",
input_type="search_document",
)cohere_rerank
Rerank documents by relevance.
cohere_rerank(
query="What is AI?",
documents=["AI is great", "Python is a language"],
model="rerank-english-v3.0",
top_n=10,
)cohere_classify
Classify texts.
cohere_classify(
texts=["This is great", "This is terrible"],
model="embed-english-v3.0",
)cohere_summarize
Summarize text.
cohere_summarize(
text="Long text to summarize...",
model="command",
length="medium",
format="paragraph",
)cohere_list_models
List available Cohere models.
cohere_list_models()Pricing
Cohere offers pay-per-token pricing. Check https://cohere.ai/pricing for details.
Deploy to Dedalus
Push to GitHub (public repo)
Add Server → Connect GitHub repo
Set
COHERE_API_KEYas Required CredentialDeploy
License
MIT
This server cannot be installed
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Servers
- AlicenseAqualityDmaintenanceAn MCP server that enables AI applications to access 20+ model providers (including OpenAI, Anthropic, Google) through a unified interface for text and image generation.230MIT
- Alicense-qualityCmaintenanceMCP server that provides tools to interact with the LiteLLM proxy API, enabling LLM completions, embeddings, image generation, and admin operations.10MIT
- Alicense-qualityBmaintenanceMCP server that enables agents to dynamically switch between multiple AI models (OpenAI, Anthropic, Google, etc.) with unified protocol-driven configuration and capability discovery.Apache 2.0
- AlicenseAqualityBmaintenanceA Model Context Protocol server for OpenAI API access via AceDataCloud, enabling chat completions, image generation, text embeddings, and more from MCP-compatible clients.111MIT
Related MCP Connectors
MCP server for AI dialogue using various LLM models via AceDataCloud
MCP server for Argo RPG Platform — connects AI assistants to campaign data via OAuth2
MCP server providing access to the Scorecard API to evaluate and optimize LLM systems.
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/madaoQ/cohere-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server