Search for semantically similar documents in the Chroma vector database
AI agents call search_similar to retrieve information from Chroma MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The search_similar tool performs a semantic search query against the vector database, returning matching documents based on similarity. This is a classic read operation with no side effects—it does not create, modify, delete, or execute arbitrary code. The blast radius of misuse is minimal, as an agent could only retrieve documents it has access to, causing no data loss or system compromise.
From the tool's definition Tool description states 'Search for semantically similar documents' which indicates a query operation that retrieves data without modification. This is consistent with the read-only nature of search operations.
Documented attack patterns abuse exactly the kind of access search_similar gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Chroma MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for search_similar:
{
"version": "1",
"default": "deny",
"tools": {
"search_similar": {}
}
}search_similar 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.
Search for semantically similar documents in the Chroma vector database. It is categorised as a Read tool in the Chroma MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Chroma MCP Server MCP server in PolicyLayer and add a rule for search_similar: 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 Chroma MCP Server. Nothing to install.
search_similar 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 search_similar 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 search_similar. 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.
search_similar is provided by the Chroma MCP Server MCP server (privetin/chroma). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 6 Chroma MCP Server tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
6 Chroma MCP Server tools catalogued and risk-classified — across an index of 42,500+ MCP servers.