Context-efficient Model Context Protocol (MCP) server for Jaeger distributed tracing
Wellknown found it in public sources; nobody has proven control of it yet. Claiming takes one click if the repository is under your GitHub account, or a small file on your domain otherwise. Verified owners get the badge, 15-minute checks, status alerts, edits that outrank crawled data, and a ranking boost.
Agents can do it too: POST https://wellknown.network/api/v1/claims with {"agent":"mcp-server-jaeger","method":"well_known_file"} — machine-readable steps at claim.json, guide at /docs/claim.
Everything here was measured by our prober or read from a registry. Nothing is self-reported.
Attributed to the source that supplied each field. Treated as claims, not facts.
<div align="center"> # ⚡ Jaeger MCP Server **Context-Efficient Observability & Distributed Tracing for AI Agents** [](https://pypi.org/project/mcp-server-jaeger/) [](https://modelcontextprotocol.io/) [](https://python.org) [](https://github.com/modelcontextprotocol/python-sdk) [](https://www.jaegertracing.io/) [](LICENSE) *Empower LLMs and AI coding assistants (Claude Desktop, Cursor, Antigravity, OpenCode, Windsurf) to inspect microservice topologies, triage performance bottlenecks, and pinpoint root-cause errors in distributed systems without blowing up context windows.* --- [🚀 Quickstart](#-quickstart) • [🎯 Why Jaeger MCP?](#-why-jaeger-mcp) • [🛠️ Tools Reference](#️-tools-reference) • [🔌 Client Configurations](#-client-configurations) • [🏗️ Architecture](#️-architecture) • [🧪 Testing & Debugging](#-testing--debugging) --- </div> ## 🎯 Why Jaeger MCP? Distributed traces in production systems easily contain **hundreds to thousands of spans**, deep call graphs, and megabytes of JSON tags and log events. If an AI assistant ingests an entire raw trace: 1. 💸 **Context Window Explosion:** Traces consume tens of thousands of tokens per prompt. 2. 📉 **Hallucinations & Noise:** LLMs struggle to locate relevant errors buried beneath healthy spans. 3. 🐌 **High Latency & Costs:** Huge payloads slow down resp…
Mapped onto the structured taxonomy from declared text and observed tool names. Confidence shown for derived entries.
Every source is kept verbatim. Field changes are logged as events.