What is self-inspect-mcp?

self-inspect-mcp is an MCP (Model Context Protocol) server by ejentum in the Autonomous Agents category. Send a thought, get one metathought that makes your agent inspect its own assumptions. Keyless.

How do I connect self-inspect-mcp to Claude, Cursor, or another MCP client?

self-inspect-mcp is a remote MCP server — add its endpoint (https://api.ejentum.com/self-inspect-mcp) to your client's MCP configuration (for example with "claude mcp add", or under "mcpServers" in Cursor's mcp.json) and restart the client.

Is self-inspect-mcp open source?

Yes — the source code is public at github.com/ejentum/self-inspect-mcp, with 5 GitHub stars.

Can AI agents pay to use self-inspect-mcp?

Not yet through Loomal — self-inspect-mcp is listed as a free directory entry. If its maintainer verifies ownership, they can set per-call USDC pricing that agents pay over x402, with settlement on Base.

self-inspect-mcp

MCP server by github.com/ejentum/self-inspect-mcp

Send a thought, get one metathought that makes your agent inspect its own assumptions. Keyless.

5 starsnpm: self-inspect-mcpRemote-capable

About self-inspect-mcp

self-inspect-mcp is an MCP (Model Context Protocol) server published by ejentum in the official MCP registry, listed under Autonomous Agents on Loomal. Send a thought, get one metathought that makes your agent inspect its own assumptions. Keyless.

self-inspect-mcp runs as a hosted remote over streamable-http — MCP clients connect directly to its endpoint, with nothing to install locally. It also ships as an npm package (self-inspect-mcp), so any MCP client that can launch a local process can run it.

Development happens in the open at github.com/ejentum/self-inspect-mcp, where the project has earned 5 GitHub stars.

Use self-inspect-mcp with your agent

Claude Code · one command

claude mcp add --transport http self-inspect-mcp https://api.ejentum.com/self-inspect-mcp

Claude Desktop, Cursor & other MCP clients · config

{
  "mcpServers": {
    "self-inspect-mcp": {
      "url": "https://api.ejentum.com/self-inspect-mcp"
    }
  }
}

streamable-httphttps://api.ejentum.com/self-inspect-mcp

npmself-inspect-mcp

Frequently asked questions

What is self-inspect-mcp?: self-inspect-mcp is an MCP (Model Context Protocol) server by ejentum in the Autonomous Agents category. Send a thought, get one metathought that makes your agent inspect its own assumptions. Keyless.
How do I connect self-inspect-mcp to Claude, Cursor, or another MCP client?: self-inspect-mcp is a remote MCP server — add its endpoint (https://api.ejentum.com/self-inspect-mcp) to your client's MCP configuration (for example with "claude mcp add", or under "mcpServers" in Cursor's mcp.json) and restart the client.
Is self-inspect-mcp open source?: Yes — the source code is public at github.com/ejentum/self-inspect-mcp, with 5 GitHub stars.
Can AI agents pay to use self-inspect-mcp?: Not yet through Loomal — self-inspect-mcp is listed as a free directory entry. If its maintainer verifies ownership, they can set per-call USDC pricing that agents pay over x402, with settlement on Base.

More Autonomous Agents MCP servers

claude-flow

59.1k

AI orchestration with hive-mind swarms, neural networks, and 87 MCP tools for enterprise dev.

tldraw

47.7k

Draw and visually collaborate with your agents on tldraw's canvas.

OpenMetadata

14.2k

Official OpenMetadata MCP: governed context and business semantics for AI assistants and agents.

PraisonAI

8.1k

AI Agents Framework with Self Reflection and MCP support

Azure MCP Server

3.3k

All Azure MCP tools to create a seamless connection between AI agents and Azure services.

agent-device

2.7k

Let AI agents inspect, control, and debug real iOS, Android, desktop, and TV apps

Browse the full MCP server directory

Listing data from the official MCP registry and GitHub, refreshed periodically. Not affiliated with the maintainer unless claimed. Maintain self-inspect-mcp? Claim this listing free by verifying GitHub ownership, or contact us.