Agent Observability MCP server

by KryptosAI·io.github.KryptosAI/agent-observability·v1.0.7

No reviews yet

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

D54/100grade D

Write a review Install

What users say

No reviews yet

Be the first

Safety scan

D54/100

full report

Adoption

Growing

2 stars32 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 v0.1.9 · 2026-09-24 · 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 59 days ago12/15
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 54/100. Components that don't apply are left out of the denominator. Any critical finding is an F.Rubric Appeal a finding JSON

Install directly

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 (54/100). Read the Agent Observability safety report
How do I install Agent Observability?: It runs on your machine. Copy the Claude Code, Claude Desktop or Cursor 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 59 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: Protect MCP server, Basic Memory MCP server and MCP server. Compare all Agent Observability alternatives.

Alternatives to Agent Observability

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

All Agent Observability alternatives →

Protect
Fail-closed Cedar policy gate + Ed25519 signed receipts for agent tool calls. Denies on any error.
not reviewed
Growing
C
Basic Memory
Local-first knowledge management with bi-directional LLM sync via Markdown files.
not reviewed
Established
C
MCP
Authorize consequential AI agent actions before execution
not reviewed
Established
A
Agent-Native Chat
Minimal chat-first app with durable threads, actions, and the app-agent loop
not reviewed
Established
A
Ausca
Pay-per-call APIs and MCP services for agents, no accounts or keys, with verifiable receipts.
not reviewed
Established
B