MCPBastion

A local zero-trust checkpoint for the Model Context Protocol: read newline-delimited JSON-RPC, decide each message against a policy - allow, deny, redact - and write only what survives, with one audit line per message.

peterpten/MCPBastion

View on GitHub ↗

A local zero-trust checkpoint for the Model Context Protocol: read newline-delimited JSON-RPC, decide each message against a policy - allow, deny, redact - and write only what survives, with one audit line per message.

MCPBastion grew +0.0% in the last 30 days, ranks 2443rd of 2,447 in Protocols (MCP / A2A), last commit 21 days ago.

Star trajectory

32 days tracked
2026-10-213 stars today2026-11-22
Momentum

+0.0% in 30d, below the Protocols (MCP / A2A) median of +1.8%.

Maintenance

Last commit 21 days ago, staler than the median of 12d.

How it compares in Protocols (MCP / A2A)

MCPBastion
3
stars
+0.0% 30d
commit 21 days ago
Protocols (MCP / A2A) median
223
stars
+1.8% 30d
commit ~12d ago
Leader · rea
473.2k
stars
+28.6% 30d
commit today

Ranked 2443rd of 2,447 by stars.

Ranked by shared tags, then keywords, then stars
  1. OpenKeylet — Local password and credential manager for AI agents via MCP. Use passwords, API keys, SSH, and…

    +7 (+5.4%) in 30d · Committed 27d ago · Rust · MIT

    Shares Protocols (MCP / A2A), Tools & Integrations, Evaluation & Guardrails

  2. 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), Tools & Integrations

  3. An AI that administers Linux through typed, approval-gated, Ed25519-audited actions. The model selects the…

    Committed today · Rust · MIT

    Shares Protocols (MCP / A2A), Tools & Integrations, Evaluation & Guardrails

  4. A deterministic privacy boundary between your data and AI.

    -2 (-0.9%) in 30d · Committed 93d ago · Rust · MIT

    Shares Evaluation & Guardrails, Tools & Integrations, Protocols (MCP / A2A)

  5. 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, Tools & Integrations, Protocols (MCP / A2A)

  6. Independent security verification for code written by humans and AI agents. Scan, repair, then prove it —…

    +3 (+2.5%) in 30d · Committed yesterday · TypeScript · MIT

    Shares Tools & Integrations, Protocols (MCP / A2A), Evaluation & Guardrails

  7. Keep secrets and PII out of logs, Sentry, LLM prompts and commits. Reads values, not field names. Zero…

    Committed yesterday · TypeScript · MIT

    Shares Evaluation & Guardrails, Tools & Integrations, Protocols (MCP / A2A)

  8. 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), Tools & Integrations, Evaluation & Guardrails

  9. 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, Tools & Integrations, 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, Tools & Integrations, Protocols (MCP / A2A)

Language
Rust
License
MIT License
Contributors
4
Forks
0
Watchers
0
Open issues
1
Releases
4
Created
2016-12-16
Stars this week
+0

You've seen where MCPBastion stands today.

Get the moves before everyone else: the 5 Protocols (MCP / A2A) repos climbing fastest, every Tuesday.

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

Maintain MCPBastion?

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

Claim this page