agent-chaperone

agent-chaperone/agent-chaperone

Screens an AI agent's tool calls before they run and tool results before the agent reads them. An MCP proxy plus a hooks adapter for a client's built-in tools.

6 good first / help-wanted issues · TypeScript · last activity Sep 19, 2026

1 stars 0 forks 1 watchers TypeScript Apache License 2.0
agent-security ai-agents jev jev-ai mcp mcp-security mcp-tools model-context-protocol prompt-injection security typesafe typesafe-ai typesafe-jev typescript
View on GitHub Website
6 Open Issues Need Help Last updated: Sep 19, 2026

Open Issues Need Help

View All on GitHub
chore(ci): test on the Node versions the package claims to support 14 days ago
good first issue help wanted type:chore area:repo priority:low
agent-chaperone/agent-chaperone
1

Screens an AI agent's tool calls before they run and tool results before the agent reads them. An MCP proxy plus a hooks adapter for a client's built-in tools.

TypeScript
#agent-security#ai-agents#jev#jev-ai#mcp#mcp-security#mcp-tools#model-context-protocol#prompt-injection#security#typesafe#typesafe-ai#typesafe-jev#typescript
chore(bench): add hand-labeled tool calls for under-represented tool families 16 days ago
good first issue help wanted type:test area:bench priority:low
agent-chaperone/agent-chaperone
1

Screens an AI agent's tool calls before they run and tool results before the agent reads them. An MCP proxy plus a hooks adapter for a client's built-in tools.

TypeScript
#agent-security#ai-agents#jev#jev-ai#mcp#mcp-security#mcp-tools#model-context-protocol#prompt-injection#security#typesafe#typesafe-ai#typesafe-jev#typescript
chore(bench): pin the dataset sources to immutable revisions about 1 month ago
good first issue help wanted type:chore area:bench priority:low
agent-chaperone/agent-chaperone
1

Screens an AI agent's tool calls before they run and tool results before the agent reads them. An MCP proxy plus a hooks adapter for a client's built-in tools.

TypeScript
#agent-security#ai-agents#jev#jev-ai#mcp#mcp-security#mcp-tools#model-context-protocol#prompt-injection#security#typesafe#typesafe-ai#typesafe-jev#typescript
chore(bench): add benign documents that discuss prompt injection without performing it about 1 month ago
good first issue help wanted type:test area:bench priority:low
agent-chaperone/agent-chaperone
1

Screens an AI agent's tool calls before they run and tool results before the agent reads them. An MCP proxy plus a hooks adapter for a client's built-in tools.

TypeScript
#agent-security#ai-agents#jev#jev-ai#mcp#mcp-security#mcp-tools#model-context-protocol#prompt-injection#security#typesafe#typesafe-ai#typesafe-jev#typescript
chore(ci): pin third-party actions to commit SHAs about 2 months ago
good first issue help wanted type:chore area:repo priority:medium
agent-chaperone/agent-chaperone
1

Screens an AI agent's tool calls before they run and tool results before the agent reads them. An MCP proxy plus a hooks adapter for a client's built-in tools.

TypeScript
#agent-security#ai-agents#jev#jev-ai#mcp#mcp-security#mcp-tools#model-context-protocol#prompt-injection#security#typesafe#typesafe-ai#typesafe-jev#typescript
docs: link the README to the published package about 2 months ago
good first issue type:docs area:repo priority:low
agent-chaperone/agent-chaperone
1

Screens an AI agent's tool calls before they run and tool results before the agent reads them. An MCP proxy plus a hooks adapter for a client's built-in tools.

TypeScript
#agent-security#ai-agents#jev#jev-ai#mcp#mcp-security#mcp-tools#model-context-protocol#prompt-injection#security#typesafe#typesafe-ai#typesafe-jev#typescript