Return the complete raw MantisBT metadata cache: all projects with full fields, and per-project lists of users, versions, categories, plus all tags. If the cache does not exist or has expired (default TTL: 24 hours), it will automatically sync first. Use sync_metadata to force a refresh. For a li...
AI agents call get_metadata_full to retrieve information from MantisBT MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries metadata without side effects. While it accesses comprehensive project and user information (moderate sensitivity), the operation is read-only with no capability to modify, delete, or execute code. Severity is low because metadata queries have limited blast radius—information disclosure alone, assuming access controls are already in place.
From the tool's definition Tool description states it 'Return[s] the complete raw MantisBT metadata cache' including 'all projects with full fields, and per-project lists of users, versions, categories, plus all tags.' The verb 'Return' and 'get' in the tool name indicate retrieval…
Attacks that exploit this kind of access
Return the complete raw MantisBT metadata cache: all projects with full fields, and per-project lists of users, versions, categories, plus all tags. If the cache does not exist or has expired (default TTL: 24 hours), it will automatically sync first. Use sync_metadata to force a refresh. For a lightweight overview use get_metadata instead. It is categorised as a Read tool in the MantisBT MCP Server MCP Server, which means it retrieves data without modifying state.
Register the MantisBT MCP Server MCP server in PolicyLayer and add a rule for get_metadata_full: 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 MantisBT MCP Server. Nothing to install.
get_metadata_full 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_metadata_full 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_metadata_full. 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_metadata_full is provided by the MantisBT MCP Server MCP server (@dpesch/mantisbt-mcp-server). 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 →