Composite government intelligence tool. Given a company name, keyword, or NAICS code, simultaneously queries: (1) USASpending.gov for federal contract awards, (2) GitHub for the company's repo activity, (3) Hacker News for developer community awareness, and (4) their product changelog for release...
Accepts freeform code/query input (query)
Part of the Freshcontext MCP server. Enforce policies on this tool with Intercept, the open-source MCP proxy.
AI agents call extract_gov_landscape to retrieve information from Freshcontext 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 extract_gov_landscape 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:
extract_gov_landscape:
rules:
- action: allowSee the full Freshcontext policy for all 17 tools.
Agents calling read-class tools like extract_gov_landscape 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.
Composite government intelligence tool. Given a company name, keyword, or NAICS code, simultaneously queries: (1) USASpending.gov for federal contract awards, (2) GitHub for the company's repo activity, (3) Hacker News for developer community awareness, and (4) their product changelog for release velocity. Answers: Who is winning government contracts in this space? Are they actually building? Does the dev community know about them? Returns a unified 4-source timestamped report. Unique — not available in any other MCP server.. It is categorised as a Read tool in the Freshcontext MCP Server, which means it retrieves data without modifying state.
Add a rule in your Intercept YAML policy under the tools section for extract_gov_landscape. You can allow, deny, rate-limit, or validate arguments. Then run Intercept as a proxy in front of the Freshcontext MCP server.
extract_gov_landscape 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 extract_gov_landscape 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 extract_gov_landscape. 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.
extract_gov_landscape is provided by the Freshcontext MCP server (freshcontext-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