MCP.Market

Agent Observability MCP server

by KryptosAI·io.github.KryptosAI/agent-observability·v1.0.7·2 stars
No reviews yet

Trace AI agent execution: every tool call, every error, every dollar. Open source, local-first.

D48/100grade D
Write a reviewInstall
What users say
No reviews yet
Be the first
Safety scan
D48/100

full report

Adoption
New

2 stars97 downloads/wk

Reviews

Write one

Nobody has reviewed Agent Observability yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

Agent Observability tools (6)

write = sends, deletes, buys or posts

Read from the package source without running it. The installed server may list more.

  • check_session

    Check the current session status — tool call count, error count, grade estimate, and session duration

  • end_session

    End an agent observability session and compute the grade

  • get_last_session

    Get the most recent session's summary including grade, errors, and cost

  • get_session_stats

    Get aggregate stats across all sessions — total sessions, total tool calls, total cost, grade distribution

  • log_tool_call

    Log a tool call made by the agent for observability tracking

  • start_session

    Start a new agent observability session to track tool calls, tokens, and errors

Public scan report

scanner v0.1.10 · 2026-11-06 · same rubric, same numbers if you re-run it

1 high2 medium
  • Code scan7 source files scanned3/25
  • –Live reliabilityno gateway calls yet and no remote to proben/a
  • –Tool poisoningtools not inspected (local package is not executed); not countedn/a
  • Auth qualitylocal package, no credentials required12/15
  • Maintenancelast push 101 days ago8/15
  • Maintainer identityregistry namespace matches repository owner; GitHub account older than a year8/10

Findings (3)

  • mediumnpm install lifecycle script presentinstall.script
  • highShell command built from a string (injection risk)exec.shell-concat
    cli.js: … exec } = require('child_process'); exec(`open http://localhost:${port} 2>/dev/null || xdg-open http://localhost:${port} 2>/dev/null`); await startServ…
  • mediumnpm install lifecycle script presentinstall.script
    package.json: …bs": "./cli.js" }, "scripts": { "postinstall": "node scripts/postinstall.mjs || true",…
Overall 48/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

How Agent Observability compares

Against every graded AI and agents MCP server, from our own scans and uptime checks. Updated after each scan run.

Safety score
48/100
higher than 10% of 4,456 AI and agents servers
Tools
6
the typical AI and agents server has 7
Tools that change things
0%
typical: 3%. Fewer write tools means less an agent can break
GitHub stars
2
more than 65% of 2,733 AI and agents servers
Downloads a week
97
more than 60% of 1,712 AI and agents servers with a package

What its tools let an agent do: 5 read · 1 run or deploy

Install Agent Observability in Claude Code, Cursor or VS Code

Runs npx -y agent-obs on your machine. Read the scan report first; the gateway never runs local packages.

claude mcp add agent-observability -- npx -y agent-obs
Add to Cursor

Agent Observability: common questions

Is Agent Observability MCP server safe?
Not recommended: it is graded D (48/100). Read the Agent Observability safety report
How do I install Agent Observability?
It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
Does Agent Observability need an API key?
Not as far as the registry entry and our scan can tell: no credentials are declared or required.
Is Agent Observability maintained?
The last commit was 111 days ago (2026-07-27). The latest release is v1.0.7.
What can I use instead of Agent Observability?
Servers from other publishers that do the same job: Basic Memory MCP server, HOL Guard MCP server and Decionis MCP server.
How does Agent Observability compare with other AI and agents MCP servers?
safety score 48/100 (higher than 10% of 4,456 AI and agents servers); tools 6 (the typical AI and agents server has 7); tools that change things 0% (typical: 3%. Fewer write tools means less an agent can break). Full comparison.

Alternatives to Agent Observability

Same job from other publishers: the closest match first, then the best rated.

  • Basic Memory
    Local-first knowledge management with bi-directional LLM sync via Markdown files.
    B
  • HOL Guard
    Local-first AI agent security evidence and approval workflows through HOL Guard's stdio MCP server.
    A
  • Decionis
    Authorize consequential AI agent actions before execution
    A
  • Agent-Native Chat
    Minimal chat-first app with durable threads, actions, and the app-agent loop
    A
  • haiku.rag
    Local-first agentic RAG with citations - hybrid search, reranking, multimodal document retrieval
    A

More from KryptosAI →