// SCAN REPORT

Nrepl

3 tools. 2 can modify or destroy data without limits.

2 write tools that can modify data. Rate limits recommended.

Last updated: 5 Jul 2026

2 can modify or destroy data

1 read-only

3 tools total

Verified server · catalogue entry verified 05/07/2026 · full schemas captured for 3 of 3 tools

How to control Nrepl ↓

TOOL MAP

What Nrepl exposes to your agents

Read (1) Write / Execute (2) Destructive / Financial (0)

Running more than one server? Check your whole stack →

CONTEXT-WINDOW COST

What Nrepl costs in tokens

371 tokens of tool definitions, loaded on every request

0.2% of a 200k context window

176 heaviest tool: eval_form

Full per-tool breakdown → Model it in the token calculator →

MOST DANGEROUS TOOLS

High Risk

The most dangerous Nrepl tools

Execute · High connect This tool establishes a network connection to an nREPL (networked REPL) server, which is an external operation with side effects. Execute · Critical eval_form This tool executes arbitrary Clojure code in a running REPL environment.

2 of Nrepl's 3 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Nrepl

PolicyLayer is an MCP gateway — it sits between your AI agents and Nrepl, and nothing reaches the server without passing your rules. These are the rules we recommend:

Cap read operations

{
  "get_ns_vars": {
    "limits": [
      {
        "counter": "get_ns_vars_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

Controls API costs and prevents retry loops from exhausting upstream rate limits.

Create a free account and register Nrepl — nothing to install.
Add these rules — paste them, or build them visually. Tune the limits to your setup.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

ENFORCE POLICY ON NREPL →

Instant setup, no code required.

FULL CATALOGUE

All 3 Nrepl tools

EXECUTE 2 tools

Execute connect Connect to an nREPL server. Example: (connect {:host "localhost" :port 1234}) Execute eval_form Evaluate Clojure code in a specific namespace or the current one. Examples: - Define and call a function: {"co

READ 1 tools

Read get_ns_vars Get all public vars (functions, values) in a namespace with their metadata and current values. Example: - List

FAQ

Questions about Nrepl

Is the Nrepl MCP server safe to use without restrictions? +

The Nrepl server is primarily read-only with 1 read tools. While it cannot modify data, an agent in a retry loop can make thousands of API calls per minute, exhausting rate limits and running up costs. Rate limiting is still recommended.

How many tools does the Nrepl MCP server expose? +

3 tools across 2 categories: Read, Write. 1 are read-only. 2 can modify, create, or delete data.

How do I enforce a policy on Nrepl? +

Register the Nrepl MCP server in PolicyLayer, apply the suggested rules above (adjust the limits to your use case), and point your AI client at the PolicyLayer proxy URL instead of the server directly. Your agents keep the same tools; PolicyLayer evaluates every call against policy before it executes. Nothing to install, live in minutes.

Enforce policy on every Nrepl tool call.

Deterministic rules across all 3 Nrepl tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON NREPL →

Instant setup, no code required.

3 Nrepl tools catalogued and risk-classified — across an index of 43,000+ MCP servers.