AI agents call get_project_decisions to retrieve information from CoordMCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The 'get_' prefix and the server's stated purpose of providing 'decision tracking' and 'shared memory' indicate this tool retrieves previously stored decisions. This is a read-only query operation with no side effects, no code execution, and no data modification or deletion. Even if misused by an agent, it would only expose historical project decisions without enabling harmful actions.
From the tool's definition Tool name 'get_project_decisions' indicates a retrieval operation with the prefix 'get_', which typically queries or fetches data without modification.
Attacks that exploit this kind of access
get_project_decisions. It is categorised as a Read tool in the CoordMCP MCP Server, which means it retrieves data without modifying state.
Register the Coord MCP server in PolicyLayer and add a rule for get_project_decisions: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches CoordMCP. Nothing to install.
get_project_decisions is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the get_project_decisions rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for get_project_decisions. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
get_project_decisions is provided by the Coord MCP server (siddiquesahabaj/coordmcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →