Fetches URL content, converts HTML to markdown (JSON is chunked by key paths, plain text indexed directly), persists it in a searchable knowledge base, and returns a small preview window per source. The raw page bytes never enter your conversation \u2014 they live in storage and you retrieve any ...
AI agents use ctx_fetch_and_index to create or update resources in Context Mode — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Context Mode environment.
The tool fetches external URL content and writes/stores it persistently in a knowledge base (indexing). It creates new stored data (reversibly), so Write is the appropriate category. It does not execute code or destructively delete data. The severity is medium because it can ingest arbitrary external URLs into a persistent knowledge base, which could introduce malicious or unintended content.
From the tool's definition Fetches URL content, converts HTML to markdown...persists it in a searchable knowledge base
Documented attack patterns abuse exactly the kind of access ctx_fetch_and_index gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Context Mode, and nothing reaches the server without passing your rules. This is the rule we recommend for ctx_fetch_and_index:
{
"version": "1",
"default": "deny",
"tools": {
"ctx_fetch_and_index": {
"limits": [
{
"counter": "ctx_fetch_and_index_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}ctx_fetch_and_index 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.
Fetches URL content, converts HTML to markdown (JSON is chunked by key paths, plain text indexed directly), persists it in a searchable knowledge base, and returns a small preview window per source. The raw page bytes never enter your conversation \u2014 they live in storage and you retrieve any section on-demand via ctx_search. Caching: every fetch is cached on disk and reused for repeat calls within the TTL window. The default TTL is 24 hours; override per-call with the \. It is categorised as a Write tool in the Context Mode MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Context Mode MCP server in PolicyLayer and add a rule for ctx_fetch_and_index: 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 Context Mode. Nothing to install.
ctx_fetch_and_index 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 ctx_fetch_and_index 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 ctx_fetch_and_index. 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.
ctx_fetch_and_index is provided by the Context Mode MCP server (mksglu/context-mode). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Context Mode, 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.
11 Context Mode tools catalogued and risk-classified — across an index of 43,000+ MCP servers.