Low Risk

decision_search

Search past decisions to understand why things are the way they are

Accepts freeform code/query input (query)

Part of the Session Forge MCP server. Enforce policies on this tool with Intercept, the open-source MCP proxy.

session-forge Read Risk 2/5

AI agents call decision_search to retrieve information from Session Forge 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 decision_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.

session-forge.yaml
tools:
  decision_search:
    rules:
      - action: allow

See the full Session Forge policy for all 15 tools.

Tool Name decision_search
Category Read
Risk Level Low

View all 15 tools →

Agents calling read-class tools like decision_search have been implicated in these attack patterns. Read the full case and prevention policy for each:

Browse the full MCP Attack Database →

Other tools in the Read risk category across the catalogue. The same policy patterns (rate-limit, allow) apply to each.

What does the decision_search tool do? +

Search past decisions to understand why things are the way they are. It is categorised as a Read tool in the Session Forge MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on decision_search? +

Add a rule in your Intercept YAML policy under the tools section for decision_search. You can allow, deny, rate-limit, or validate arguments. Then run Intercept as a proxy in front of the Session Forge MCP server.

What risk level is decision_search? +

decision_search is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit decision_search? +

Yes. Add a rate_limit block to the decision_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.

How do I block decision_search completely? +

Set action: deny in the Intercept policy for decision_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.

What MCP server provides decision_search? +

decision_search is provided by the Session Forge MCP server (session-forge). Intercept sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policies on Session Forge

Open source. One binary. Zero dependencies.

npx -y @policylayer/intercept
github.com/policylayer/intercept →
// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.