Get filtered task context based on agent type (PM/worker/QC). Server-side context isolation for multi-agent workflows. PM agents get full context (100%), workers get minimal context (<10% - only files, dependencies, requirements), QC agents get requirements + worker output for verification. Imple...
AI agents call get_task_context to retrieve information from M I M I R Multi Agent Intelligent Memory & Insight Repository without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and returns task context from a graph database with role-based filtering (PM/worker/QC agents). It has no side effects, does not execute code or workflows, does not modify data, and does not delete anything. The severity is low because context retrieval poses minimal risk even if an agent misuses filters; the worst case is information disclosure or incorrect context routing, not system-level harm.
From the tool's definition Tool 'get_task_context' retrieves filtered task context; the description uses verbs 'get' and 'get' with no mentions of creation, modification, deletion, execution, or financial operations.
Documented attack patterns abuse exactly the kind of access get_task_context gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and M I M I R Multi Agent Intelligent Memory & Insight Repository, and nothing reaches the server without passing your rules. This is the rule we recommend for get_task_context:
{
"version": "1",
"default": "deny",
"tools": {
"get_task_context": {}
}
}get_task_context is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
All 13 M I M I R Multi Agent Intelligent Memory & Insight Repository tools →
Get filtered task context based on agent type (PM/worker/QC). Server-side context isolation for multi-agent workflows. PM agents get full context (100%), workers get minimal context (<10% - only files, dependencies, requirements), QC agents get requirements + worker output for verification. Implements 90%+ context reduction for worker agents. It is categorised as a Read tool in the M I M I R Multi Agent Intelligent Memory & Insight Repository MCP Server, which means it retrieves data without modifying state.
Register the M I M I R Multi Agent Intelligent Memory & Insight Repository MCP server in PolicyLayer and add a rule for get_task_context: 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 M I M I R Multi Agent Intelligent Memory & Insight Repository. Nothing to install.
get_task_context 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_task_context 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_task_context. 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_task_context is provided by the M I M I R Multi Agent Intelligent Memory & Insight Repository MCP server (orneryd/mimir). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 13 M I M I R Multi Agent Intelligent Memory & Insight Repository tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
13 M I M I R Multi Agent Intelligent Memory & Insight Repository tools catalogued and risk-classified — across an index of 42,500+ MCP servers.