Log inSubmit server
Agentic Observability MCP logo

Agentic Observability MCP

MCP server for tracing agent actions, tracking token costs, monitoring tools, and detecting anomalies.

InstallRepository
Full README Compare alternatives Embed widget Claim this listing

Install Agentic Observability MCP

Pick your client, then add it in one click or paste the config.

STDIONode.js
~/Library/Application Support/Claude/claude_desktop_config.json
claude_desktop_config.json
{
  "mcpServers": {
    "agentic-observability-mcp": {
      "command": "npx",
      "args": [
        "agentic-observability-mcp"
      ]
    }
  }
}

Settings → Developer → Edit Config, merge this into mcpServers, then fully quit and reopen Claude Desktop.

We couldn’t confirm it starts correctly

We ran the install command but it didn't respond within our test window — this can mean a slow first-time install rather than a real problem.

npx agentic-observability-mcp

No response to initialize.

This is an experimental automated check and can have false negatives — missing environment variables, a slow cold install, etc. It doesn’t necessarily mean something’s wrong. Last checked 2d ago.

Overview

Agentic Observability MCP MCP server records LLM calls, tool invocations, decisions, errors, and session metadata through MCP tools. It calculates token costs using built-in pricing tables for major Anthropic, OpenAI, Google, and Mistral models, while also reporting latency, failures, and session totals. Reach for it when developing or operating agents that need cost visibility, performance data, anomaly checks, or decision audit records. The v1 implementation stores data in memory, so records are lost when the server restarts.

Use cases

  • Trace agent decisions and tool activity
  • Track token usage and model costs
  • Monitor tool latency and failures
  • Detect loops and cost spikes
  • Review session audit records

Key features

  • Agent action tracing
  • Automatic token cost calculation
  • Session and cost reporting
  • Tool performance monitoring
  • Anomaly detection
  • Static pricing and best-practice resources

Security & health

What it can reach and how reliably it runs — from our own checks, not the maintainer’s claims.

ActiveLast checked 3d ago

Recent health check succeeded.

Supply-chain signal

No high-severity advisories surfaced by our automated scan.

Critical 0High 0Medium 0Low 0

Scanned 7d ago via OSV.dev · agentic-observability-mcp (npm)

Adoption & maintenance

Factual signals from GitHub, npm, and our automated checks — not a rating.

Last commit6mo agoMost recent push to the default branch.
Install checkInconclusiveDidn't respond in our test window — often a slow first install.
Directory activity2 viewsConfig copies, upvotes, and views on AllMCPs.

How Agentic Observability MCP works

What Agentic Observability MCP MCP server does

Agentic Observability MCP MCP server provides MCP tools for collecting operational data from AI agent runs. It can record general actions such as decisions, model requests, tool calls, and errors; track input and output tokens; calculate call and session costs; and summarize activity across a session.

The server also evaluates recorded activity for several predefined conditions. These include unusually high costs, elevated tool failure rates, long-running tool calls, repeated calls with identical parameters, and excessive token use. Decision traces can serve as audit records when their descriptions include the relevant reasoning or context.

How it works

An agent sends events to the server as it works. Use trace_agent_action for broad action records, track_token_usage for LLM usage, and log_tool_call for MCP tool performance data. get_cost_report aggregates spending by dimensions such as model, provider, tool, or session. get_session_summary combines costs, tokens, tool statistics, errors, model details, and duration into a session report.

detect_anomaly checks stored activity for the supported anomaly categories. Loop detection identifies the same tool and parameters being used at least three times. The documented thresholds include a tool error rate above 30 percent and tool latency above 10 seconds; cost and token checks use configured thresholds.

Two static resources are available: observability://pricing exposes the pricing data used for calculations, and observability://best-practices provides an observability guidance document.

Setup and configuration

Agentic Observability MCP MCP server requires Node.js 18 or newer and runs without API keys. Install it through an MCP client by launching npx agentic-observability-mcp as a stdio server. Claude Desktop and Claude Code use ~/.claude/settings.json or a project .mcp.json; Cursor uses .cursor/mcp.json. Windsurf and VS Code use their MCP configuration files with the same command and argument pattern.

The server has no documented environment variables or external service configuration requirements. It includes pricing entries for selected Anthropic, OpenAI, Google, and Mistral models, as well as zero-cost self-hosted models. Custom pricing can be supplied when the built-in entries do not match the model being tracked.

Tools and capabilities

  • Record agent actions with metadata and timestamps.
  • Calculate LLM call costs from token counts and model pricing.
  • Group costs by model, provider, tool, or session.
  • Measure tool-call latency, success, failure, and error details.
  • Produce session-level reports and run anomaly checks.
  • Expose pricing and observability guidance as MCP resources.

Limitations and notes

The first version uses in-memory Maps for storage. Restarting the server removes collected traces, costs, and session data. The repository describes a future storage layer that could be replaced with Redis or Postgres, but those backends are not part of the documented v1 setup.

The pricing table covers named model families rather than every possible provider or model. Cost accuracy therefore depends on selecting the correct model or providing custom pricing.

Read the full README View source on GitHub

Reviews

No reviews yet — be the first to share how it worked for you.

Frequently Asked Questions about Agentic Observability MCP

Agentic Observability MCP is an MCP server that connects AI agent workflows with tracing, token accounting, tool monitoring, anomaly detection, and audit records. Its main tools record actions, track LLM usage, log tool calls, summarize sessions, report costs, and check for cost spikes, errors, latency problems, loops, and excessive token use.

Install it by adding an MCP stdio entry that runs `npx agentic-observability-mcp`. Claude Desktop and Claude Code use their Claude settings or project MCP file, while Cursor uses `.cursor/mcp.json`; Windsurf and VS Code use their MCP configuration files.

Yes, Agentic Observability MCP works with Cursor through `.cursor/mcp.json`. Add an MCP server entry with `npx` as the command and `agentic-observability-mcp` as its argument.

No, the server does not require API keys. It runs with Node.js 18 or newer and has no documented external service dependencies beyond the MCP SDK and Zod.

No, v1 stores data in memory, so traces, costs, and session records are lost when the server restarts. The repository describes Redis or Postgres as possible future storage replacements, not as available v1 backends.

Related MCP servers

All in Monitoring All alternatives
Add a badge to your READMEShow it’s listed — live SVG, Markdown or HTML.

AllMCPs Directory Badge

Full Badge Customizer

Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.

Badge Style:
Live Dynamic SVG PreviewAgentic Observability MCP AllMCPs Directory Badge
Markdown (GitHub README)
[![AllMCPs](https://allmcps.com/api/badge/agentic-observability-mcp?style=directory)](https://allmcps.com/mcp/agentic-observability-mcp)
HTML Embed
<a href="https://allmcps.com/mcp/agentic-observability-mcp"><img src="https://allmcps.com/api/badge/agentic-observability-mcp?style=directory" alt="Agentic Observability MCP on AllMCPs" /></a>