What tools does the run-mcp MCP server provide?

run-mcp exposes 12 tools: call_mcp_primitive, connect_to_mcp, disconnect_from_mcp, get_mcp_server_stderr, get_server_notifications, list_available_mcp_servers, list_mcp_primitives, mcp_server_status, read_result, reconnect_to_mcp, subscribe_to_resource, validate_mcp_server. This list was read from the published package source; the server runs locally and has no endpoint to query.

Does run-mcp require an API key?

Not known. run-mcp has not been successfully queried, so its authentication requirements are unverified.

Connection check local install

run-mcp

A thin MCP client for humans and agents — run any Model Context Protocol server, call its tools, read its stderr, and reconnect after each edit. REPL, headless CLI, or an MCP server your agent drives. No client config edits, no restarts.

Browser automation

Tools 12

GitHub stars —

Installs / wk 187

Licence MIT

Transport stdio

Last checked never

Tools & capabilities

12 tools

Read from the published package source — this server runs locally, so there is no endpoint to query. Names are taken from the code, not observed at runtime, and descriptions are often absent.

call_mcp_primitive from source

connect_to_mcp from source

disconnect_from_mcp from source

get_mcp_server_stderr from source

get_server_notifications from source

list_available_mcp_servers from source

list_mcp_primitives from source

mcp_server_status from source

read_result from source

reconnect_to_mcp from source

subscribe_to_resource from source

validate_mcp_server from source