annotate_caid

THE RISK

Low Risk

Why annotate_caid needs a policy

This tool looks up and returns annotation information for a ClinGen Allele Registry ID (CAid). It is a read/query operation that retrieves variant annotation data without modifying, deleting, or executing anything.

From the tool's definition Annotate a ClinGen Allele Registry ID — retrieves annotation data for a given ID with no side effects

Documented attack patterns abuse exactly the kind of access annotate_caid gives an agent:

POLICY

How to control annotate_caid

PolicyLayer is an MCP gateway — it sits between your AI agents and OpenCRAVAT, and nothing reaches the server without passing your rules. This is the rule we recommend for annotate_caid:

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "annotate_caid": {}
  }
}

annotate_caid is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.

Create a free account and register OpenCRAVAT — nothing to install.
Add this policy — paste it, or build it visually.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

CAP THIS TOOL →

Free to start. No card required.

EXPLORE

Related tools and policies

More OpenCRAVAT tools

Read get_fields Get the fields returned for annotators including data type, name, human readable title, an Read list_annotators List metadata about the OpenCRAVAT annotators that will be run. Read protein_variant_to_genomic_hgvs Provide a protein-level missense notation variant (eg BRAF V600E) and get genomic HGVS cha Read annotate_hgvs Annotate an hgvs identifier. Accepts genomic (g.), coding (c.), and protein (p.) level HGV Read annotate_rsid Annotate a dbSNP rsID Read annotate_variant Annotate a genomic variant (chromosome, position, reference allele, alternate allele

All 7 OpenCRAVAT tools →

Read tools on other servers

M-Team MCP Server get_torrent_detail YouTube MCP Server search_channel Android Forensics ADB MCP Server parse_browser_history 0xarchive web3_challenge

Go deeper

The MCP Attack Database → Documented attack patterns against MCP deployments — and the policies that stop them.
Data exfiltration → How read access becomes an exfiltration channel when chained with untrusted content.
MCP token cost → What connecting this server costs in context-window tokens on every request.
Rate Limiting MCP Tool Calls: A Practical Guide →
MCP Security: Why Prompt Guardrails Aren't Enough →

FAQ

Questions about annotate_caid

What does the annotate_caid tool do? +

Annotate a ClinGen Allele Registry ID. It is categorised as a Read tool in the OpenCRAVAT MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on annotate_caid? +

Register the OpenCRAVAT MCP server in PolicyLayer and add a rule for annotate_caid: 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 OpenCRAVAT. Nothing to install.

What risk level is annotate_caid? +

annotate_caid is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit annotate_caid? +

Yes. Add a rate_limit block to the annotate_caid 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.

How do I block annotate_caid completely? +

Set action: deny in the PolicyLayer policy for annotate_caid. 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.

What MCP server provides annotate_caid? +

annotate_caid is provided by the OpenCRAVAT MCP server (karchinlab/oc-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every OpenCRAVAT tool call.

Start from OpenCRAVAT, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

CHECK YOUR STACK →