12 tools. 6 can modify or destroy data without limits.
2 destructive tools with no built-in limits. Policy required.
Last updated:
Destructive tools (chroma_delete_collection, chroma_delete_documents) permanently delete resources. There is no undo. An agent calling these in a retry loop causes irreversible damage.
Write operations (chroma_add_documents, chroma_create_collection, chroma_modify_collection) modify state. Without rate limits, an agent can make hundreds of changes in seconds — faster than any human can review or revert.
Intercept sits between your agent and ChromaDB. Every tool call checked against your policy before it executes — so your agent can do its job without breaking things.
npx -y @policylayer/intercept scan -- npx -y @chroma-mcp chroma_delete_collection:
rules:
- action: deny Destructive tools should never be available to autonomous agents without human approval.
chroma_add_documents:
rules:
- rate_limit: 30/hour Prevents bulk unintended modifications from agents caught in loops.
chroma_get_collection_count:
rules:
- rate_limit: 60/minute Controls API costs and prevents retry loops from exhausting upstream rate limits.
Yes. The ChromaDB server exposes 2 destructive tools including chroma_delete_collection, chroma_delete_documents. These permanently remove resources with no undo. Intercept blocks destructive tools by default so they never reach the upstream server.
The ChromaDB server has 4 write tools including chroma_add_documents, chroma_create_collection, chroma_modify_collection. Set rate limits in your policy file -- for example, rate_limit: 10/hour prevents an agent from making more than 10 modifications per hour. Intercept enforces this at the transport layer.
12 tools across 3 categories: Destructive, Read, Write. 6 are read-only. 6 can modify, create, or delete data.
One line change. Instead of running the ChromaDB server directly, prefix it with Intercept: intercept -c chromadb.yaml -- npx -y @@chroma-mcp. Download a pre-built policy from policylayer.com/policies/chromadb and adjust the limits to match your use case.
Starter policies available for each. Same risk classification, same one-command setup.
Set budgets, approvals, and hard limits across MCP servers.
npx -y @policylayer/intercept init