AI agents call mtrkr_companion_get to retrieve information from Mtrkr without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The '_get' suffix typically indicates data retrieval. While the description is uninformative, the broader context of wallet intelligence tools and sibling functions that are analysis/inspection-focused suggests this is likely a read operation (fetching companion wallet data).
From the tool's definition Tool name 'mtrkr_companion_get' follows a read-like naming pattern ('get'). The description is empty, limiting direct evidence, but contextual clues from sibling tools (analyze, compare, decode, inspect, scan, resolve) suggest this server provides query and…
Attacks that exploit this kind of access
mtrkr_companion_get. It is categorised as a Read tool in the Mtrkr MCP Server, which means it retrieves data without modifying state.
Register the Mtrkr MCP server in PolicyLayer and add a rule for mtrkr_companion_get: 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 Mtrkr. Nothing to install.
mtrkr_companion_get 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 mtrkr_companion_get 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 mtrkr_companion_get. 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.
mtrkr_companion_get is provided by the Mtrkr MCP server (mtrkr-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 →