Evaluate Clojure code in a specific namespace or the current one. Examples: - Define and call a function: {"code": "(defn greet [name] (str \"Hello, \" name \"!\"))(greet \"World\"))"} - Reload code: {"code": "(clj-reload.core/reload)"} - Evaluate in a specific namespace: {"code": "(clojure.repl....
AI agents invoke eval_form to trigger actions in Nrepl. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
| Parameter | Type | Required | Description |
|---|---|---|---|
ns | string | — | Optional namespace to evaluate in. Changes persist for subsequent evaluations. |
code | string | Yes | Clojure code to evaluate |
Parameters from the server's own tool schema.
This tool executes arbitrary Clojure code in a running REPL environment. An AI agent could run any code including filesystem operations, network calls, shell commands, data deletion, or other destructive/financial actions. The blast radius is critical since there are no apparent sandboxing constraints and the examples already show reloading code and syncing dependencies.
From the tool's definition "Evaluate Clojure code in a specific namespace or the current one" — arbitrary code execution via nREPL
Risk signalsAccepts freeform code/query input (code)
Attacks that exploit this kind of access
Evaluate Clojure code in a specific namespace or the current one. Examples: - Define and call a function: {"code": "(defn greet [name] (str \"Hello, \" name \"!\"))(greet \"World\"))"} - Reload code: {"code": "(clj-reload.core/reload)"} - Evaluate in a specific namespace: {"code": "(clojure.repl.deps/sync-deps)", "ns": "user"}. It is categorised as a Execute tool in the Nrepl MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
eval_form accepts 2 parameters: ns, code. Required: code. The full parameter table on this page comes from the server's own tool schema.
Register the Nrepl MCP server in PolicyLayer and add a rule for eval_form: 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 Nrepl. Nothing to install.
eval_form is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the eval_form 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 eval_form. 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.
eval_form is provided by the Nrepl MCP server (nrepl-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →