behavior_lookup
Use when the agent has a specific (crate, fn_name) pair and wants to know what inputs it actually accepts at runtime — e.g. (crate='jiff', fn_name='Timestamp::from_str') for methods, (crate='ascii85', fn_name='decode') for free functions. fn_name accepts BOTH qualified (Type::method / module::fn)...
This record as markdown: /tools/dev-codeitall-codeitall/behavior-lookup.md
What behavior_lookup does on Codeitall
AI agents call behavior_lookup to retrieve information from Codeitall without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
| Parameter | Type | Required | Description |
|---|---|---|---|
crate | string | Yes | |
inputs | array | — | |
fn_name | string | Yes |
Parameters from the server's own tool schema.
Why behavior_lookup is rated Low
behavior_lookup is a read-only tool that retrieves and reports observed runtime behavior data for Rust crate APIs. It performs lookups and returns observation tables without side effects, state changes, or code execution. This is a pure information retrieval operation, fitting the Read category.
From the tool's definition Tool description states it 'wants to know what inputs it actually accepts at runtime' and 'Returns the probe observation table verbatim from the substrate' — these are query operations that retrieve runtime behavior data without modifying or executing…
Attacks that exploit this kind of access
The rule that runs behavior_lookup safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Codeitall, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For behavior_lookup, this is the rule to start with:
behavior_lookup is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Codeitall, apply this rule, and every behavior_lookup call is checked against it from then on.
Questions about behavior_lookup
Use when the agent has a specific (crate, fn_name) pair and wants to know what inputs it actually accepts at runtime — e.g. (crate='jiff', fn_name='Timestamp::from_str') for methods, (crate='ascii85', fn_name='decode') for free functions. fn_name accepts BOTH qualified (Type::method / module::fn) and bare (method / fn) forms — the matcher tries the exact input first, then the alternate form; the matched_fn_name response field records the substitution when one happened. Returns the probe observation table verbatim from the substrate: each row is (input, outcome=ok|err|panic, value or error variant). Pass an optional inputs array to filter to specific input strings. On a zero-hit the response carries a diagnostics block (received_crate, received_fn_name, closest_crates, closest_fns_in_crate, hint) so the agent can self-correct without a dead-end round-trip. The substrate's discrimination findings live here — runtime behaviour the docs are silent or wrong about. It is categorised as a Read tool in the Codeitall MCP Server, which means it retrieves data without modifying state.
behavior_lookup accepts 3 parameters: crate, inputs, fn_name. Required: crate, fn_name. The full parameter table on this page comes from the server's own tool schema.
Register the Codeitall MCP server in PolicyLayer and add a rule for behavior_lookup: 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 Codeitall. Nothing to install.
behavior_lookup 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 behavior_lookup 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 behavior_lookup. 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.
behavior_lookup is provided by the Codeitall MCP server (https://api.codeitall.dev/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Codeitall, and thousands of servers like it.
This server
Across the catalogue