Agentic Observability MCP
Built for teams running LLM agents who need to know what's burning tokens and when things go sideways. Exposes tools like trace_agent_action for logging decisions, track_token_usage with automatic cost calculation across Claude, GPT, Gemini, and Mistral models, and detect_anomaly to catch cost spikes, stuck loops, and error rate problems before they become incidents. Stores everything in memory (ephemeral, v1 architecture). Reach for this when you're instrumenting an agent framework or need session-level cost breakdowns without building your own telemetry stack. The get_cost_report tool groups spending by model or session, and loop detection flags when an agent calls the same tool with identical params three times in a row.
- tools
- 6
- transport
- STDIO
- last updated
- Apr 23, 2026
Tools
6 toolsPublic tool metadata for what this MCP can expose to an agent.
trace_agent_actionLog any agent action (tool calls, LLM requests, decisions, errors) with metadata and timestamps
Log any agent action (tool calls, LLM requests, decisions, errors) with metadata and timestamps
No parameter schema in public metadata yet.
track_token_usageTrack token usage per LLM call with automatic cost calculation from built-in pricing tables (Claude, GPT, Gemini, Mistral)
Track token usage per LLM call with automatic cost calculation from built-in pricing tables (Claude, GPT, Gemini, Mistral)
No parameter schema in public metadata yet.
get_cost_reportAggregate cost breakdown across sessions, grouped by model, provider, tool, or session
Aggregate cost breakdown across sessions, grouped by model, provider, tool, or session
No parameter schema in public metadata yet.
log_tool_callLog MCP tool calls with latency, success/failure, and error details
Log MCP tool calls with latency, success/failure, and error details
No parameter schema in public metadata yet.
get_session_summaryFull session report: cost, tokens, tool stats, error count, model breakdown, duration
Full session report: cost, tokens, tool stats, error count, model breakdown, duration
No parameter schema in public metadata yet.
detect_anomalyFlag unusual patterns: cost_spike, error_rate, latency_spike, loop_detection, token_explosion
Flag unusual patterns: cost_spike, error_rate, latency_spike, loop_detection, token_explosion
No parameter schema in public metadata yet.
Sponsors
Agent CaffeineSponsoredClose your lid, come back to finished work
SnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthly
WaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthly
knobsSponsoredSee your site on any phone, any day, in any languageReadme
agentic-observability-mcp
AI agent observability for MCP. Tracing, cost tracking, performance monitoring, anomaly detection, and audit trails — all via Model Context Protocol.
Why This Exists
AI agents burn tokens, call tools, make decisions, and sometimes get stuck in loops. You need to know what they're doing, what it costs, and when something goes wrong. No existing MCP server provides unified agent observability. This one does.
Track every LLM call, every tool invocation, every decision — with automatic cost calculation and anomaly detection.
What It Does
Tracing
trace_agent_action— Log any agent action (tool calls, LLM requests, decisions, errors) with metadata and timestamps
Details
- Repository
- github.com/mdfifty50-boop/agent-observability-mcp
- Categories
- AI & LLM Tools, Monitoring & Observability
- Package
agentic-observability-mcp- Transport
- STDIO
- Registry
- MCP registry, active
More from mdfifty50-boop
Related AI & LLM Tools MCP servers
View all
Crawl4AI RAGcoleam00/mcp-crawl4ai-ragProvides web crawling, RAG, and knowledge-graph capabilities for AI agents with a Supabase-backed vector store.2.2Kstars
Ask Geminilykhoyda/ask-llmBridge Claude with Gemini CLI for AI-to-AI collaboration, code review, and second opinions19stars
Langchain Mcpbaixianger/langchain-mcpLangChain/LangGraph/DeepAgents knowledge + LangGraph agent debugging (Polly-like)5stars
Agent Immunedenial-web/agent-immuneAI agent security: prompt injection detection, semantic memory, output scanning, prompt hardening0stars
Authenticated Mcp Agentmikerawsonnz/gosce-agentsJWT-gated LLM gateway: authenticate (bcrypt/JWT), then run a LangChain-on-Vertex Gemini completion.0starsLlm Observability Orchestrationmikerawsonnz/gosce-agentsRun a prompt through a LangChain (system + human) chain over Gemini on Vertex AI; optional LangSmith0stars