Agent Observability MCP
Agent Observability is an MCP server that records structured agent logs, costs, and compliance audit trails to a hosted API.
About
Agent Observability is an MCP server that sends agent activity to a hosted observability API: structured logs, cost tracking, and compliance audit trails. Developers who already ship Claude Code or Cursor automations install it when printf debugging and spreadsheet token math stop scaling—you need a durable record of what the agent did, what it cost, and what auditors might ask for later. Configure stdio package agent-observability-mcp with AGENT_OBS_API_KEY obtained via the service register endpoint; AGENT_OBS_API_URL defaults to the Railway-hosted production API unless you self-route. Version 1.1.0 in the MCP registry. It belongs on Operate → monitoring alongside error and infra tooling, though you can wire it during late Ship if you are hardening before launch. It is an integration, not a replacement for full APM, but it narrows the gap for agent-specific telemetry.
- Structured logging for agent runs via MCP
- Cost tracking aligned to agent API usage
- Compliance-oriented audit trail export
- npm agent-observability-mcp with stdio transport v1.1.0
- AGENT_OBS_API_KEY from POST /v1/register; optional AGENT_OBS_API_URL override
Agent Observability MCP by the numbers
- Data as of Aug 10, 2026 (Skillselion catalog sync)
claude mcp add --env AGENT_OBS_API_KEY=YOUR_AGENT_OBS_API_KEY --env AGENT_OBS_API_URL=YOUR_AGENT_OBS_API_URL agent-observability-mcp -- npx -y agent-observability-mcpAdd your badge
Show developers this MCP server is listed on Skillselion. Paste this into your README.
| Package | agent-observability-mcp |
|---|---|
| Transport | STDIO |
| Auth | Required |
What it does
Centralize agent run logs, token spend, and compliance audit trails from MCP instead of scattered console output.
Who is it for?
Best when you're running paid or regulated agent workflows and need cost visibility and auditable run history without building a custom observability stack.
Skip if: Hobby one-off prompts with no production traffic or teams already standardized on a full enterprise APM with agent plugins.
What you get
After setup with AGENT_OBS_API_KEY, agent runs emit structured telemetry and audit-ready trails through MCP instead of ephemeral chat logs.
- Centralized structured logs for agent runs
- Cost tracking data tied to agent activity
- Compliance-oriented audit trail records
By the numbers
- Registry version 1.1.0
- Default API base: https://api-production-0c55.up.railway.app (overridable via AGENT_OBS_API_URL)
- 2 environment variables documented (1 required secret)
Recommended MCP Servers
Agent Audit MCPImmutable audit trail for agent-to-agent interactions2
Agentguard47 MCPRead-only MCP server for coding-agent traces, alerts, costs, usage, and budget health.4
Agentic Observability MCPAgent tracing, cost tracking, anomaly detection for LLM agentsAgent Incident Relay MCPAgent Incident Relay MCP — Article 73 5-clock broadcaster.
Agent Infra MCP18 tools: agent memory, API drift detection, and HMAC-signed trust receipts
Agentmonitorrelay MCPAI agent run monitoring with incident replay and SLA receipts.How it compares
Agent-focused observability MCP, not a generic log shipper skill.
FAQ
Who is Agent Observability MCP for?
Developers and small teams operating AI agents in production who need logging, spend tracking, and audit trails from MCP.
When should I use Agent Observability MCP?
Use it in Operate when agents run repeatedly in the wild and you need monitoring beyond the IDE transcript.
How do I add Agent Observability MCP to my agent?
Register for an API key (POST /v1/register), set AGENT_OBS_API_KEY, optionally AGENT_OBS_API_URL, and add agent-observability-mcp stdio to your MCP config.