Notes with zero backlinks AND low semantic neighbours (isolation = 1 - max cosine).
AI agents call find_orphans to retrieve information from brainMD without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a read-only analysis of existing markdown notes by checking their connectivity (backlinks) and semantic relationships (vector similarity). It has no side effects—it does not create, modify, delete, or execute code. The blast radius if misused is minimal; an AI agent could at worst retrieve a list of unused notes, which is informational only.
From the tool's definition Tool name 'find_orphans' and description indicate it retrieves and queries notes based on backlink counts and semantic similarity metrics (cosine distance). No parameters suggest modification, deletion, or execution of external operations.
Documented attack patterns abuse exactly the kind of access find_orphans gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and brainMD, and nothing reaches the server without passing your rules. This is the rule we recommend for find_orphans:
{
"version": "1",
"default": "deny",
"tools": {
"find_orphans": {}
}
}find_orphans 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.
Notes with zero backlinks AND low semantic neighbours (isolation = 1 - max cosine). It is categorised as a Read tool in the brainMD MCP Server, which means it retrieves data without modifying state.
Register the brainMD MCP server in PolicyLayer and add a rule for find_orphans: 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 brainMD. Nothing to install.
find_orphans 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 find_orphans 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 find_orphans. 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.
find_orphans is provided by the brainMD MCP server (mi4uu/brain.md). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from brainMD, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
17 brainMD tools catalogued and risk-classified — across an index of 43,000+ MCP servers.