Find MCP servers that are semantically similar to a reference server. Use when a user picked a candidate but wants alternatives — e.g. 'like this but safer', 'like this but free', 'what else does this'. Reuses the catalog's gte-small embeddings: the reference server's embedding is the query vecto...
Part of the MCP Marketplace server.
Free to start. No card required.
AI agents call similar_to to retrieve information from MCP Marketplace without modifying any data. This is common in research, monitoring, and reporting workflows where the agent needs context before taking action. Because read operations don't change state, they are generally safe to allow without restrictions -- but you may still want rate limits to control API costs.
Even though similar_to only reads data, uncontrolled read access can leak sensitive information or rack up API costs. An agent caught in a retry loop could make thousands of calls per minute. A rate limit gives you a safety net without blocking legitimate use.
Read-only tools are safe to allow by default. No rate limit needed unless you want to control costs.
{
"version": "1",
"default": "deny",
"tools": {
"similar_to": {}
}
}See the full MCP Marketplace policy for all 7 tools.
These attack patterns abuse exactly the kind of access similar_to gives an agent. Each links to the full case and the policy that stops it:
Other read tools across the catalogue. The same approach applies to each: allow, with a rate cap to control cost.
Find MCP servers that are semantically similar to a reference server. Use when a user picked a candidate but wants alternatives — e.g. 'like this but safer', 'like this but free', 'what else does this'. Reuses the catalog's gte-small embeddings: the reference server's embedding is the query vector. Returns servers sorted by cosine similarity (highest first), excluding the reference itself. Each result carries the same security/risk/pricing fields as search_servers so callers can immediately compare on security_score, has_critical_findings, and pricing.. It is categorised as a Read tool in the MCP Marketplace MCP Server, which means it retrieves data without modifying state.
Register the MCP Marketplace MCP server in PolicyLayer and add a rule for similar_to: 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 Marketplace. Nothing to install.
similar_to 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 similar_to 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 similar_to. 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.
similar_to is provided by the MCP Marketplace MCP server (https://mcp-marketplace.io/api/mcp/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 7 MCP Marketplace tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
4,600+ MCP servers and 31,000+ tools scanned and risk-classified.