Fetch a web/docs URL as clean, token-optimized markdown from Slipstream's shared cache (use INSTEAD of a raw web fetch). The first agent pays the crawl; every agent after gets ~90% fewer tokens. Surfaces warnings other agents left on the page. Pass known_hash to skip re-reading unchanged content ...
Risk signalsAccepts URL/endpoint input (url) · Bulk/mass operation — affects multiple targets
Part of the Slipstream server.
Free to start. No card required.
AI agents call cached_fetch to retrieve information from Slipstream 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 cached_fetch 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": {
"cached_fetch": {}
}
}See the full Slipstream policy for all 8 tools.
These attack patterns abuse exactly the kind of access cached_fetch 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.
Fetch a web/docs URL as clean, token-optimized markdown from Slipstream's shared cache (use INSTEAD of a raw web fetch). The first agent pays the crawl; every agent after gets ~90% fewer tokens. Surfaces warnings other agents left on the page. Pass known_hash to skip re-reading unchanged content (delta), or section to fetch just one heading (progressive disclosure). Returns a contentHash you can pass as known_hash next time.. It is categorised as a Read tool in the Slipstream MCP Server, which means it retrieves data without modifying state.
Register the Slipstream MCP server in PolicyLayer and add a rule for cached_fetch: 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 Slipstream. Nothing to install.
cached_fetch 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 cached_fetch 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 cached_fetch. 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.
cached_fetch is provided by the Slipstream MCP server (https://slipstream-pi.vercel.app/api/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 8 Slipstream 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.