Gowthaman90

Gowthaman90/mcp-bastion

Reliability + security proxy for the Model Context Protocol (MCP): self-healing connections, runtime tool-security (rug-pull/poisoning detection), and a compliance-mapped audit trail.

2 stars 1 forks 2 watchers TypeScript Apache License 2.0

agentic ai ai-agents ai-security anthropic claude llm llm-security mcp model-context-protocol nist-ai-rmf owasp proxy typescript

5 Open Issues Need Help Last updated: Jul 8, 2026

Open Issues Need Help

View All on GitHub

feat: add a bastion__reconnect_all control tool about 3 hours ago

enhancement good first issue

Gowthaman90/mcp-bastion

2

Reliability + security proxy for the Model Context Protocol (MCP): self-healing connections, runtime tool-security (rug-pull/poisoning detection), and a compliance-mapped audit trail.

TypeScript

#agentic#ai#ai-agents#ai-security#anthropic#claude#llm#llm-security#mcp#model-context-protocol#nist-ai-rmf#owasp#proxy#typescript

docs: add a Troubleshooting / FAQ section to the README about 3 hours ago

documentation good first issue

Gowthaman90/mcp-bastion

2

Reliability + security proxy for the Model Context Protocol (MCP): self-healing connections, runtime tool-security (rug-pull/poisoning detection), and a compliance-mapped audit trail.

TypeScript

#agentic#ai#ai-agents#ai-security#anthropic#claude#llm#llm-security#mcp#model-context-protocol#nist-ai-rmf#owasp#proxy#typescript

feat: add an OTLP audit sink about 4 hours ago

enhancement help wanted

Gowthaman90/mcp-bastion

2

Reliability + security proxy for the Model Context Protocol (MCP): self-healing connections, runtime tool-security (rug-pull/poisoning detection), and a compliance-mapped audit trail.

TypeScript

#agentic#ai#ai-agents#ai-security#anthropic#claude#llm#llm-security#mcp#model-context-protocol#nist-ai-rmf#owasp#proxy#typescript

test: add a Postgres upstream integration fixture about 4 hours ago

good first issue

Gowthaman90/mcp-bastion

2

Reliability + security proxy for the Model Context Protocol (MCP): self-healing connections, runtime tool-security (rug-pull/poisoning detection), and a compliance-mapped audit trail.

TypeScript

#agentic#ai#ai-agents#ai-security#anthropic#claude#llm#llm-security#mcp#model-context-protocol#nist-ai-rmf#owasp#proxy#typescript

docs: add a Zed setup recipe to the README about 4 hours ago

documentation good first issue

Gowthaman90/mcp-bastion

2

Reliability + security proxy for the Model Context Protocol (MCP): self-healing connections, runtime tool-security (rug-pull/poisoning detection), and a compliance-mapped audit trail.

TypeScript

#agentic#ai#ai-agents#ai-security#anthropic#claude#llm#llm-security#mcp#model-context-protocol#nist-ai-rmf#owasp#proxy#typescript