MCPolly MCP Server

Agent-native observability for AI agents. MCP server with web dashboard, alerting, and semantic search. Built with Rust, Axum, SQLite, and HTMX.

Local serverstdio

What is the MCPolly MCP Server?

Agent-native observability for AI agents. MCP server with web dashboard, alerting, and semantic search. Built with Rust, Axum, SQLite, and HTMX.

What the server does

Agent-native status, observability, and knowledge platform for AI agents. MCPolly is an MCP server that lets AI agents report their progress, errors, and state in real time — and gives humans a unified web dashboard to monitor everything. Agents can also index and semantically search product documents to stay aligned.

Credentials and setup notes

  • Ollama installed and running with all-minilm model pulled (for embeddings) - Port 3000 (or configured port) available

More MCP options

Compare MCP servers by category, or browse hosted MCP servers if you prefer an endpoint over a local process.

Maintainer setup documentation.

Configuration

  • Ollama installed and running with all-minilm model pulled (for embeddings) - Port 3000 (or configured port) available
VariableDescriptionRequired
MCPOLLY_URLEndpoint or connection string the server talks to.Yes
MCPOLLY_API_KEYCredential the server authenticates with.Yes
DATABASE_URLEndpoint or connection string the server talks to.Yes
OLLAMA_URLEndpoint or connection string the server talks to.Yes

Example prompts to try

  • “Use MCPolly to Method.”
  • “Use MCPolly to GET.”
  • “Use MCPolly to POST.”

Frequently asked questions

MCPolly exposes an MCP Streamable HTTP endpoint (`/mcp`) using JSON‑RPC over HTTP with SSE streaming. Agents connect directly via HTTP; an optional stdio binary (`mcpolly_mcp`) is available for platforms that do not support HTTP transport.