The following steps show how to deploy the Context7 MCP server and a chatbot agent using Meshagent in a temporary Meshagent Room. When the Room closes, the tools and chatbot are also removed—perfect for experimentation or development.

​
1. Install Meshagent CLI with all features:

pip install "meshagent[all]"

​
2. Sign up and authenticate:

See Meshagent CLI Getting Started for instructions.

​
3. Launch the MCP server into a test Room

meshagent service test --room=test --role=agent --image=meshagent/mcp-context7:latest \
  --env MESHAGENT_PORT=8001 \
  --port="num=8001 path=/webhook liveness=/ type=meshagent.callable" \
  --name=mcp-context7-service-test
  • Starts a Meshagent Room with a temporary MCP server agent.
  • Rooms will close if inactive or when the test is complete.

​
4. Add a chatbot with the Context7 toolkit to the Room

meshagent chatbot join --room=test --agent-name=mcp-context7 --name=mcp-context7 --toolkit=mcp-context7
  • Starts a chatbot agent that can use the Context7 tools in the Room.
  • Multiple toolkits or agents may be used in the same Room.
  • The command output will include a link to open the Room in your browser.

​
5. Visit the Room and Try It!

Open the provided Room link in your browser and send a message to the agent. You can interact with the MCP server tools via chat—e.g., ask for documentation or resolve a library ID.

​
Project Level Deployment (Persistent Services)

For production or team flows, you can deploy the MCP server and chatbot as persistent Meshagent services at the project level. They will automatically join every new Room in your project, so you no longer need to host them locally or launch them for each session.

​
1. Create the Context7 MCP server service (project-wide)

meshagent service create --role=agent --image=meshagent/mcp-context7:latest \
  --env MESHAGENT_PORT=8001 \
  --port="num=8001 path=/webhook liveness=/ type=meshagent.callable" \
  --name=mcp-context7-service

​
2. Deploy the Context7 chatbot agent (project-wide)

meshagent service create --image="meshagent/cli:latest" \
  --port="num=9001 path=/agent liveness=/ type=meshagent.callable participant_name=mcp-context7-chatbot" \
  --env="MESHAGENT_PORT=9001" \
  --name="mcp-context7-chatbot-service" \
  --command="meshagent chatbot service --agent-name=mcp-context7-chatbot --toolkit=mcp-context7"
  • These services will be started automatically in every new Room in your Meshagent project.
  • You no longer need to run MCP servers or chatbots locally—everything is managed via Meshagent’s cloud deployment.

​
Tools Available from Context7 MCP Server

Context7 MCP Server provides two main tools to power AI agents and chatbots for code documentation retrieval:

​
get-library-docs

Fetches up-to-date documentation for a library. You must call resolve-library-id first to obtain the exact Context7-compatible library ID required to use this tool, unless the user explicitly provides a library ID in the format /org/project or /org/project/version in their query. Parameters:
NameTypeDescription
context7CompatibleLibraryIDstringExact Context7-compatible library ID (e.g., /mongodb/docs, /vercel/next.js)
tokensnumber (optional)Max number of tokens to retrieve (default: 10,000)
topicstring (optional)Topic to narrow focus (e.g., ‘hooks’, ‘routing’)

​
resolve-library-id

Resolves a package/product name to a Context7-compatible library ID and returns a list of matching libraries. Selection Process:
  • Name similarity (exact match preferred)
  • Description relevance
  • Documentation coverage (prioritize higher code snippet count)
  • Trust score (7-10 preferred)
Usage:
  1. Call this tool with the plain package/library name.
  2. Returns the best-matching library ID (and brief explanation).
  3. If no good match is found, it will suggest query refinements.
Parameters:
NameTypeDescription
libraryNamestringName of the library/package to search for

​
Meshagent Resources

Happy collaborating, coding, and documenting in real time!