mcp-observatory

Free, MIT-licensed MCP security testing from ClearFrame. Scan, audit, compare, and review locally; continue in the ClearFrame CLI or Mac app.

clearframes/mcp-observatory

View on GitHub ↗

Free, MIT-licensed MCP security testing from ClearFrame. Scan, audit, compare, and review locally; continue in the ClearFrame CLI or Mac app.

mcp-observatory grew -16.2% in the last 30 days, ranks 670th of 872 in Evaluation & Guardrails, actively maintained, last commit yesterday.

Star trajectory

140 days tracked
2026-07-04114 stars today2026-11-22
Momentum

-16.2% in 30d, below the Evaluation & Guardrails median of +1.4%.

Maintenance

Last commit yesterday, fresher than the median of 15d.

How it compares in Evaluation & Guardrails

mcp-observatory
114
stars
-16.2% 30d
commit yesterday
Evaluation & Guardrails median
235
stars
+1.4% 30d
commit ~15d ago
Leader · impeccable
114.7k
stars
+0.0% 30d
commit today

Ranked 670th of 872 by stars.

Ranked by shared tags, then keywords, then stars
  1. Open-source AI security verification for model artifacts, live endpoints, MCP servers, and recorded agent…

    -26 (-10%) in 30d · Committed today · Python · Apache-2.0

    Shares Evaluation & Guardrails, Protocols (MCP / A2A)

  2. +1 (+0.5%) in 30d · Committed 32d ago · JavaScript · AGPL-3.0

    Shares Protocols (MCP / A2A), Evaluation & Guardrails

  3. Wireshark-like forensic analysis for Model Context Protocol communications Capture, inspect, and investigate…

    +0 (+0.0%) in 30d · Committed 209d ago · JavaScript · Other license

    Shares Evaluation & Guardrails, Protocols (MCP / A2A)

  4. Tamper-evident audit trails for AI agents: hash-chained Runtime Records, dependency-free, verifiable by…

    +2 (+2.4%) in 30d · Committed 21d ago · Python · Apache-2.0

    Shares Evaluation & Guardrails, Protocols (MCP / A2A)

  5. AI agent supervision framework in alpha. Decide MCP tool calls by policy and check recorded runs…

    -1 (-7.7%) in 30d · Committed today · Go · Apache-2.0

    Shares Evaluation & Guardrails, Protocols (MCP / A2A)

  6. Stop your AI from making things up — it proposes, deterministic tools decide, every claim checked against…

    +39 (+3.0%) in 30d · Committed 20d ago · Python · MIT

    Shares Protocols (MCP / A2A), Evaluation & Guardrails

  7. Open-source AI agent firewall for MCP security and agent egress. Scans mediated HTTP, MCP, A2A, and WebSocket…

    +55 (+5.7%) in 30d · Committed today · Go · Apache-2.0

    Shares Evaluation & Guardrails, Protocols (MCP / A2A)

  8. Runtime security for AI apps and agents: prompt injection detection, tool-call authorization, sensitive-data…

    +7 (+1.0%) in 30d · Committed 2d ago · TypeScript · Apache-2.0

    Shares Evaluation & Guardrails, Protocols (MCP / A2A)

  9. A secure* runtime for autonomous AI agents. Policy from plain-English constitutions…

    +68 (+11%) in 30d · Committed 2d ago · TypeScript · Apache-2.0

    Shares Evaluation & Guardrails, Protocols (MCP / A2A)

  10. Open-source adversary emulation for AI agents and MCP servers.

    +5 (+0.9%) in 30d · Committed 18d ago · TypeScript · Other license

    Shares Evaluation & Guardrails, Protocols (MCP / A2A)

Language
TypeScript
License
MIT License
Contributors
10
Forks
14
Watchers
0
Open issues
7
Releases
112
Created
2026-03-19
Stars this week
-7

You've seen where mcp-observatory stands today.

Get the moves before everyone else: the 5 Evaluation & Guardrails repos climbing fastest, every Tuesday.

Free weekly digest. Double opt-in, unsubscribe anytime.

Maintain mcp-observatory?

Claim this page to add your own call-to-action.

Claim this page