Index or reindex all documents in the knowledge base. Mutating — modifies the vector index. CPU/IO intensive for full_rebuild (~6 min for 200 docs). Args: force: If True, smart reindex (detects changed files + rebuilds BM25 index). Fast (~5s for 200 docs). Use after manually editing files on disk...
AI agents use reindex_documents to create or update resources in Knowledge Rag — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Knowledge Rag environment.
The primary action is rebuilding/modifying the vector index, which is a Write operation. However, the 'full_rebuild' mode deletes all existing vectors before re-embedding, which has a destructive sub-step. Since the data is re-embedded from source documents (not permanently lost), the net effect is a Write/rebuild rather than a true irreversible deletion — the documents themselves remain intact.
From the tool's definition 'Index or reindex all documents', 'Mutating — modifies the vector index', 'nuclear rebuild — deletes all vectors and re-embeds everything from scratch'
Risk signalsBulk/mass operation — affects multiple targets
Documented attack patterns abuse exactly the kind of access reindex_documents gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Knowledge Rag, and nothing reaches the server without passing your rules. This is the rule we recommend for reindex_documents:
{
"version": "1",
"default": "deny",
"tools": {
"reindex_documents": {
"limits": [
{
"counter": "reindex_documents_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}reindex_documents stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Index or reindex all documents in the knowledge base. Mutating — modifies the vector index. CPU/IO intensive for full_rebuild (~6 min for 200 docs). Args: force: If True, smart reindex (detects changed files + rebuilds BM25 index). Fast (~5s for 200 docs). Use after manually editing files on disk outside of add_document(). full_rebuild: If True, nuclear rebuild — deletes all vectors and re-embeds everything from scratch. Use only if the embedding model changed or the index is corrupted. Returns: JSON string with indexing statistics (docs processed, added, skipped, errors). Usage: Normal workflow does not require this — add_document(), update_document(), and add_from_url() all auto-index on call. Use force=True only after direct filesystem edits. Use full_rebuild=True only for model upgrades or index corruption. No arguments runs a fast incremental pass. It is categorised as a Write tool in the Knowledge Rag MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Knowledge Rag MCP server in PolicyLayer and add a rule for reindex_documents: 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 Knowledge Rag. Nothing to install.
reindex_documents is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the reindex_documents 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 reindex_documents. 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.
reindex_documents is provided by the Knowledge Rag MCP server (lyonzin/knowledge-rag). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Knowledge Rag, 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.
12 Knowledge Rag tools catalogued and risk-classified — across an index of 43,000+ MCP servers.