Return the full (non-expired) blackboard state.
AI agents call blackboard_dump to retrieve information from Mcp Research Collective without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves the entire blackboard (shared belief store) without modifying anything. It is purely a read/query operation. Severity is medium because the blackboard may contain sensitive research data, agent states, or intermediate findings — exposing the full state could leak confidential multi-agent collaboration context.
From the tool's definition Return the full (non-expired) blackboard state
Attacks that exploit this kind of access
Return the full (non-expired) blackboard state. It is categorised as a Read tool in the Mcp Research Collective MCP Server, which means it retrieves data without modifying state.
Register the Mcp Research Collective MCP server in PolicyLayer and add a rule for blackboard_dump: 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 Research Collective. Nothing to install.
blackboard_dump 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 blackboard_dump 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 blackboard_dump. 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.
blackboard_dump is provided by the Mcp Research Collective MCP server (siegkat/mcp-agent-blackboard). 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 →