MCP Observatory
7m ago Tracked 59,479 Last 7m ago 24h 2,575
pypi Python analyzed 0.8.0

agentgraph-server

v0.8.0
pypi

A local-first CLI and MCP server that turns selected digital sources into a searchable graph for the AI agent you already use.

maintainer
—
licence
—
first seen
2026-08-16
last seen
2026-09-11
releases · 30d
7
short id
risk 5/100 · heuristic grade
A minimal inferred analyzer v33 (current)
  • capability exposure inferred + 14
  • trust mitigators mixed − 9

inferred mixed

The A–E grade is our heuristic synthesis — a "review this" prompt, not a verdict. Each factor is tagged by what backs it: attested (a verifiable record), reported (a third party's claim), or inferred (our own heuristic, e.g. permissions). See methodology.

grade last moved 1w ago · see ecosystem CVEs →

risk trajectory 1 movements
  • A · 10 → A · 5
capability exposure grade factor +14
Inferred surface — each links to servers holding it:
vulnerabilities 0 CVEs

No known CVEs for this server.

tool safety all quiet

No tool-safety findings — heuristic detectors run on the compute-risk cadence; a finding appears when a tool trips a rule.

skills & danger signals pypi-sdist
prompt-surface shipped agent-instruction files + hidden-content / dangerous-code findings — quoted from the analyzed source

analyzed v0.8.0 · analyzer v33 · 6d ago

skills & prompt files 2

  • skill agentgraph_server-0.8.0/.agents/skills/agentgraph/SKILL.md
  • skill agentgraph_server-0.8.0/.agents/skills/slack-auth/SKILL.md

danger signals6

  • over-broad OAuth scope https://mail.google.com/ agentgraph_server-0.8.0/agentgraph/demo.py :132 "web_url": "https://mail.google.com/mail/u/0/#all/atlas-maya-thread",
  • over-broad OAuth scope https://mail.google.com/ agentgraph_server-0.8.0/tests/test_connectors.py :199 "https://mail.google.com/mail/u/0/#inbox/FMfcgzQhVrDqdZqlbQxsFHmWxPVSqDnD",
  • over-broad OAuth scope https://mail.google.com/ agentgraph_server-0.8.0/tests/test_expiration.py :389 "gmail", "thread-1", "observation-1", "https://mail.google.com/thread-1", 3000
  • over-broad OAuth scope https://mail.google.com/ agentgraph_server-0.8.0/tests/test_feed_connectors.py :341 "https://mail.google.com/thread-1",
  • over-broad OAuth scope https://mail.google.com/ agentgraph_server-0.8.0/tests/test_observation.py :219 "https://mail.google.com/mail/u/0/#inbox/opaque",
  • over-broad OAuth scope https://mail.google.com/ agentgraph_server-0.8.0/tests/test_router.py :34 "https://mail.google.com/mail/u/0/#inbox/18f0c1d2e3a4b5c6",
embed badge readme-ready
live risk-grade badge preview [![MCP Observatory risk grade](https://mcpobservatory.com/servers/pypi:agentgraph-server/badge.svg)](https://mcpobservatory.com/servers/pypi:agentgraph-server/security)

Heuristic, inferred signals — false positives (legitimately powerful tools, forks, language ports) are expected. Treat each as "review this", not a verdict. See the ecosystem-wide picture on the security hub.