AI-driven semantic code search using Windsurf's Devstral model. Searches a codebase with natural language and returns relevant file paths with line ranges, plus suggested grep keywords for follow-up searches. Parameter tuning guide: - tree_depth: Controls how much directory structure the remote A...
Accepts freeform code/query input (query); High parameter count (15 properties)
Part of the Fast Context MCP server. Enforce policies on this tool with Intercept, the open-source MCP proxy.
AI agents call fast_context_search to retrieve information from Fast Context 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 fast_context_search 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.
tools:
fast_context_search:
rules:
- action: allowSee the full Fast Context policy for all 2 tools.
Agents calling read-class tools like fast_context_search have been implicated in these attack patterns. Read the full case and prevention policy for each:
Other tools in the Read risk category across the catalogue. The same policy patterns (rate-limit, allow) apply to each.
AI-driven semantic code search using Windsurf's Devstral model. Searches a codebase with natural language and returns relevant file paths with line ranges, plus suggested grep keywords for follow-up searches. Parameter tuning guide: - tree_depth: Controls how much directory structure the remote AI sees before searching. If you get a payload/size error, REDUCE this value. If search results are too shallow (missing files in deep subdirectories), INCREASE this value. Use 0 for auto depth based on project size. - max_turns: Controls how many search-execute-feedback rounds the remote AI gets. If results are incomplete or the AI didn't find enough files, INCREASE this value. If you want a quick rough answer, use 1. - include_code_snippets: Default false (lightweight mode, ~2-5KB output). Set to true to include full code snippets in the response (~45KB output). Response includes a [config] line showing actual parameters used — use this to decide adjustments on retry.. It is categorised as a Read tool in the Fast Context MCP Server, which means it retrieves data without modifying state.
Add a rule in your Intercept YAML policy under the tools section for fast_context_search. You can allow, deny, rate-limit, or validate arguments. Then run Intercept as a proxy in front of the Fast Context MCP server.
fast_context_search 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 fast_context_search rule in your Intercept 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 Intercept policy for fast_context_search. 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.
fast_context_search is provided by the Fast Context MCP server (fast-context-mcp). Intercept sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Open source. One binary. Zero dependencies.
npx -y @policylayer/intercept