This MCP server automatically instruments Python AI agents using the ioa-observe-sdk, adding OpenTelemetry-based tracing, metrics, and logs with no manual effort required.
From the registry: Add OpenTelemetry tracing to Python AI agents. Supports LangGraph, LlamaIndex, CrewAI, OpenAI SDK.
Please install the `observe-instrument-mcp` MCP server into my current AI client (that's you).
Required prerequisites (do these first if not already done):
- **LLM provider API key** — Requires an API key for a supported LLM provider (Anthropic, OpenAI, Gemini, Groq, or Ollama). Defaults to Anthropic.
Canonical MCP server config (stdio transport):
- command: `uvx`
- args: ["observe-instrument-mcp"]
- optional environment variables:
- `ANTHROPIC_API_KEY`: Required when using Anthropic models (default provider). (example: `<your-anthropic-api-key>`)
- `OPENAI_API_KEY`: Required when using OpenAI models. (example: `<your-openai-api-key>`)
- `GEMINI_API_KEY`: Required when using Google Gemini models. (example: `<your-gemini-api-key>`)
- `GROQ_API_KEY`: Required when using Groq models. (example: `<your-groq-api-key>`)
- `LLM_MODEL`: LLM model identifier. (example: `claude-sonnet-4-6`)
Note: At least one provider API key is required in practice — defaults to Anthropic.
Add this MCP server to my current client's config in the correct format for you. If you need secrets or credentials I haven't provided, ASK me — do not invent values or leave raw placeholders. After adding it, tell me how to verify the server is connected.ANTHROPIC_API_KEYrequiredRequired for Anthropic modelsOPENAI_API_KEYrequiredRequired for OpenAI modelsGEMINI_API_KEYrequiredRequired for Google Gemini modelsGROQ_API_KEYrequiredRequired for Groq modelsReal-time infrastructure monitoring with metrics, logs, alerts, and ML-based anomaly detection.
Persistent codebase knowledge graph. Survives session restarts and context compaction.
Validate oh-my-posh configurations and segment snippets against the official schema.