Fetch team-level pull request metrics from Swarmia.
AI agents call get_pull_requests to retrieve information from Mcp Swarmia without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves pre-computed pull request metrics from Swarmia without creating, modifying, or deleting any data. It is a straightforward data query operation with no side effects. The blast radius of misuse is minimal—an agent could only over-query or request metrics beyond authorization, but cannot alter engineering data or trigger external actions.
From the tool's definition Tool name 'get_pull_requests' and description 'Fetch team-level pull request metrics' indicate data retrieval with no modification. The verb 'Fetch' and context of querying 'metrics' (derived data, not operational data) confirm read-only access.
Attacks that exploit this kind of access
Fetch team-level pull request metrics from Swarmia. It is categorised as a Read tool in the Mcp Swarmia MCP Server, which means it retrieves data without modifying state.
Register the Mcp Swarmia MCP server in PolicyLayer and add a rule for get_pull_requests: 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 Mcp Swarmia. Nothing to install.
get_pull_requests 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_pull_requests 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_pull_requests. 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_pull_requests is provided by the Mcp Swarmia MCP server (smattila/mcp-swarmia). 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 →