AnythingMCP Cloud is live — 7-day free trial−30% for 3 months with START30
AnythingMCP
Connector guide8-minute read17 MCP tools7 languages

Connect Cohere to Claude via MCP: Chat and Search

Cohere with your own API key: answers from Command models with citations from your documents, embeddings for semantic search, reranking of search results, speech-to-text, parsing of document images, token counting, and the models, datasets, batches and embed jobs of the account.

HCBy HelpCode teamUpdated 8 min read Open-source on GitHub
Install Cohere on Cloud — free trialRead the step-by-step guide

No credit card · 7-day trial · Self-host alternative available

Cohere

Cohere

Let your AI use Cohere with your own API key: chat with Command models (with citations from your documents), create embeddings, rerank search results, transcribe audio, parse document images, count tokens, and check models, datasets, batches and embed jobs.

tools

17

Region

INTL

Category

Public Data

Authentication

Bearer Token

Required env vars

COHERE_API_KEY
Install in one click on Cloud

7-day free trial · No credit card

  • 7-day free trial
    No credit card required
  • GDPR & SOC 2 ready
    EU data residency, audit logs
  • Open-source on GitHub
    Open source · AGPL-3.0
  • Works with ChatGPT, Claude, Gemini
    Any MCP-compatible client

Summary

Cohere with your own API key: answers from Command models with citations from your documents, embeddings for semantic search, reranking of search results, speech-to-text, parsing of document images, token counting, and the models, datasets, batches and embed jobs of the account.

Guided setup

Connect Cohere to Claude in 2 minutes

Start a free trial on AnythingMCP Cloud, connect Cohere in the guided setup, then add your MCP URL to Claude. No code and no server to run.

Set up Cohere freeI already have an account

No credit card · 7-day trial · Self-host alternative available

AnythingMCP is listed in Claude's connector directory: add it to Claude in one click (opens in a new tab), then sign in and choose which MCP servers Claude may use.

Try asking

Example prompts for Cohere

Click any prompt to copy it. Paste into Claude, ChatGPT, Cursor, Gemini, Copilot or OpenClaw to run it against this connector.

Cohere · live via MCP
Share
Opus 4.7

Claude is AI and can make mistakes. Please double-check responses.

💡 No install? Use cloud.anythingmcp.com directly. Sign in, click Connectors → Cohere, paste your credentials, mint an MCP API key and you're done. No Docker, no git clone, no local server.

Cohere + Claude

Cohere with your own API key: answers from Command models with citations from your documents, embeddings for semantic search, reranking of search results, speech-to-text, parsing of document images, token counting, and the models, datasets, batches and embed jobs of the account.

Prerequisites

See the full setup instructions baked into the connector (visible in the in-app store when you select the connector). The required environment variables for this connector are:

COHERE_API_KEY

Step 1 — Get credentials

Setting up takes about 2 minutes. You need a Cohere account; a trial key is free.

  1. Sign up at https://dashboard.cohere.com and open API Keys (https://dashboard.cohere.com/api-keys).
  2. Copy the trial key, or create a production key after adding a payment method under Billing.
  3. Paste it into COHERE_API_KEY, without the word Bearer. The connector sends it as Authorization: Bearer and only to Cohere.
  4. Install the connector and run cohere_check_api_key or cohere_list_models to check the key.

Which tools cost money: cohere_chat, cohere_embed, cohere_rerank, cohere_transcribe_audio and cohere_parse_document run a model. With a production key every call is billed: chat per input and output token, embed per token or image, rerank per search of up to 100 documents (longer documents count as several). A trial key is free but rate limited per minute and per month and may not be used commercially. The AI asks you before large or repeated calls and sets max_tokens to cap a chat reply. cohere_tokenize, cohere_detokenize, cohere_check_api_key and all list and get tools cost nothing.

Models: ids change, so cohere_list_models (filter endpoint chat, embed or rerank) has the current list and cohere_get_model shows one model's context length, features and endpoints.

  • Chat: command-a-03-2025 (the default choice), command-a-reasoning-08-2025 (reasoning), command-a-vision-07-2025 (images), command-a-translate-08-2025 (translation), command-r7b-12-2024 (small and cheap).
  • Embed: embed-v4.0 (text and images), embed-v5.0-pro, embed-v5.0-fast, embed-multilingual-v3.0.
  • Rerank: rerank-v5.0-fast (default), rerank-v5.0-pro (more accurate), rerank-v3.5.
  • Transcription: cohere-transcribe-03-2026. Parsing: parse-v5.0.

Answers with citations: cohere_chat takes model and messages and returns the whole reply at once. Pass documents (plain strings, or objects with id and data holding title and snippet) for a grounded answer: the reply then carries message.citations pointing into them. response_format forces JSON, tools adds function calling, and thinking with type disabled turns reasoning off on reasoning models.

Semantic search: cohere_embed turns up to 96 texts (or images as data URIs) into vectors; input_type search_document is for what you store, search_query for the query. The default here is embed-v4.0 with 256 dimensions (output_dimension 256, 512, 1024 or 1536). cohere_rerank orders up to 1,000 documents by relevance to a query and returns results with index (the position in your list) and relevance_score from 0 to 1; top_n keeps only the best.

Audio and documents: cohere_transcribe_audio takes a public link to an audio file (flac, mp3, mpeg, mpga, ogg, wav, up to 10 MB through this connector) and the required language (ISO-639-1); the connector downloads the file and uploads it to Cohere. cohere_parse_document turns an image of a page (scan, photo, screenshot; public link or data URI up to 20 MB) into markdown with tables inlined, or into layout blocks. PDFs are not supported yet.

Tokens: cohere_tokenize counts the tokens of a text for a model, for example before a chat call; cohere_detokenize turns token ids back into text.

Account data: cohere_list_datasets, cohere_get_dataset and cohere_get_dataset_usage (storage used, at most 10 GB per organization); cohere_list_batches and cohere_get_batch for Batch API jobs; cohere_list_embed_jobs and cohere_get_embed_job for embed jobs.

Data formats: chat returns message.content[] (items of type text with text), finish_reason (COMPLETE, MAX_TOKENS, STOP_SEQUENCE, TOOL_CALL, ERROR) and usage.billed_units with the billed input and output tokens. Embeddings are under embeddings.float, one vector per text in order. Dates are ISO 8601, UTC.

Paging: cohere_list_models and cohere_list_batches return next_page_token; the AI passes it as page_token until it is empty. cohere_list_datasets pages with limit and offset.

Switched off at install: nothing. All 17 tools are on, and none of them deletes anything.

Limits: at most 96 texts per embed call and 1,000 documents per rerank; audio up to 10 MB and document images up to 20 MB. Trial keys have low per-minute and monthly limits.

Common errors: 400 means a bad request (for example a parameter the model does not take, or more than 96 texts); 401 a wrong key; 402 a payment method is needed (add one under Billing); 404 an unknown model, dataset, batch or job; 422 a request that could not be processed; 429 the rate limit (the AI waits instead of retrying in a loop); 499 a cancelled request; 500 and 503 are Cohere problems, retry once later.

The connector does not stream replies and does not create, cancel or delete datasets, batches or embed jobs. Classify, Summarize, Generate, connectors and fine-tuning are deprecated by Cohere and left out.

Step 2 — Install the adapter

curl -fsSL https://raw.githubusercontent.com/HelpCode-ai/anythingmcp/main/docker-compose.quickstart.yml -o docker-compose.yml
printf 'JWT_SECRET=%s\nENCRYPTION_KEY=%s\n' "$(openssl rand -hex 32)" "$(openssl rand -hex 32)" > .env
docker compose up -d

Step 3 — Add the connector in Claude

Your server URL: in AnythingMCP, open MCP Servers → the server this connector is on, and copy its URL (https://cloud.anythingmcp.com/mcp/…). Use it wherever this guide shows YOUR_SERVER_ID.

Recommended path: works on claude.ai web without editing any config file.

  1. In Claude, open Customize → Connectors.
  2. Click +, then Add custom connector.
  3. Enter a name, e.g. Cohere, and the remote MCP server URL https://cloud.anythingmcp.com/mcp/YOUR_SERVER_ID, then click Add.
  4. Click Connect and sign in to AnythingMCP (OAuth) to allow access.

All tools below appear in your chat: start typing prompts.

Available tools

ToolWhat it does
cohere_list_modelsList the Cohere models available to this key, with endpoints they serve (chat, embed, rerank), context length, features and whether they…
cohere_get_modelRead one Cohere model by name: endpoints, default endpoints, context length, features (e.g. tools, vision, reasoning), tokenizer URL and…
cohere_check_api_keyCheck that the Cohere API key is valid and active; returns valid plus the organization and owner ids
cohere_chatAsk a Cohere Command model and get its reply (Chat API v2, non-streaming)
cohere_embedTurn up to 96 texts (or images as data URIs) into embedding vectors for semantic search, clustering or classification (Embed API v2)
cohere_rerankOrder a list of documents by relevance to a query (Rerank API v2) and return the top results with their index in the list and a…
cohere_transcribe_audioTranscribe speech in an audio file to text with Cohere Transcribe
cohere_parse_documentParse an image of a document page (scan, photo, screenshot) into markdown, with tables inlined, or into layout blocks (Parse API v2)
cohere_tokenizeSplit a text into tokens with the tokenizer of a Cohere model and return the token ids and token strings, e.g. to count tokens before a…
cohere_detokenizeTurn a list of token ids back into text with the tokenizer of a Cohere model
cohere_list_datasetsList the datasets of the Cohere account (inputs for embed jobs, batches and fine-tuning) with id, name, type, validation status and…
cohere_get_datasetRead one Cohere dataset: name, type, validation status and error, schema, size and its parts
cohere_get_dataset_usageRead how much dataset storage the Cohere organization uses, in bytes (the limit is 10 GB per organization)
cohere_list_batchesList the Batch API jobs of the Cohere account with id, name, model, status, input and output dataset ids and request counts
cohere_get_batchRead one Cohere batch job: status, model, input and output dataset ids, request counts (succeeded, failed) and timestamps
cohere_list_embed_jobsList the embed jobs of the Cohere account with job id, name, status, model, input and output dataset ids and creation time
cohere_get_embed_jobRead one Cohere embed job: status (processing, complete, cancelling, cancelled, failed), model, truncate setting, input dataset and the…

Example prompts

  • "Answer the question about our refund window using only these three policy excerpts, and show which excerpt each sentence comes from."
  • "Which of these 20 product descriptions best match waterproof winter hiking boots? Rerank them and show the top 5 with scores."
  • "How many tokens does this contract text have for command-a-03-2025?"
  • "Turn the scanned invoice at https://example.com/scans/invoice-0425.png into markdown, including the line-item table."
  • "Which of my Cohere embed jobs and batches are still running, and did any of them fail?"

FAQ

Does it work with Claude Code as well as Claude Desktop? Yes, point both at https://cloud.anythingmcp.com/mcp/YOUR_SERVER_ID.

Next steps

Was this guide helpful?

Connect Cohere to Claude in 2 minutes

Start a free trial on AnythingMCP Cloud, connect Cohere in the guided setup, then add your MCP URL to Claude. No code and no server to run.

Set up Cohere freeSelf-host with DockerContact Sales

Related guides

Connectors

Cohere MCP Server: Chat, Embeddings and Reranking

Cohere with your own API key: answers from Command models with citations from your documents, embeddings for semantic search, reranking of search results, speech-to-text, parsing of document images, token counting, and the models, datasets, batches and embed jobs of the account.

Connectors

Connect Cohere to ChatGPT via MCP: Chat and Search

Cohere with your own API key: answers from Command models with citations from your documents, embeddings for semantic search, reranking of search results, speech-to-text, parsing of document images, token counting, and the models, datasets, batches and embed jobs of the account.

Connectors

Connect Cohere to Cursor via MCP: Chat and Search

Cohere with your own API key: answers from Command models with citations from your documents, embeddings for semantic search, reranking of search results, speech-to-text, parsing of document images, token counting, and the models, datasets, batches and embed jobs of the account.

Connectors

Connect Cohere to Gemini CLI via MCP

Cohere with your own API key: answers from Command models with citations from your documents, embeddings for semantic search, reranking of search results, speech-to-text, parsing of document images, token counting, and the models, datasets, batches and embed jobs of the account.

Connectors

Connect Cohere to Meta Muse via MCP

Cohere with your own API key: answers from Command models with citations from your documents, embeddings for semantic search, reranking of search results, speech-to-text, parsing of document images, token counting, and the models, datasets, batches and embed jobs of the account.

Connectors

Connect Cohere to Microsoft Copilot via MCP

Cohere with your own API key: answers from Command models with citations from your documents, embeddings for semantic search, reranking of search results, speech-to-text, parsing of document images, token counting, and the models, datasets, batches and embed jobs of the account.