// SCAN REPORT

Reprise

3 tools. 1 can modify or destroy data without limits.

1 write tool that can modify data. Rate limits recommended.

Last updated: 18 Aug 2026

1 can modify or destroy data

2 read-only

3 tools total

Community server · catalogue entry checked 18/08/2026 · full schemas captured for 3 of 3 tools

How to control Reprise ↓

TOOL MAP

What Reprise exposes to your agents

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

Running more than one server? Check your whole stack →

CONTEXT-WINDOW COST

What Reprise costs in tokens

278 tokens of tool definitions, loaded on every request

0.1% of a 200k context window

104 heaviest tool: diagnose

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

MOST DANGEROUS TOOLS

High Risk

The most dangerous Reprise tools

Execute · Medium reproduce The tool performs a non-trivial computational operation (image analysis, layer decomposition, and reproduction) that goes beyond simple data retrieval or storage write.

1 of Reprise'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 Reprise

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

Cap read operations

{
  "autodetect": {
    "limits": [
      {
        "counter": "autodetect_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 Reprise — 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 REPRISE →

Instant setup, no code required.

FULL CATALOGUE

All 3 Reprise tools

EXECUTE 1 tools

Execute reproduce Un-flatten a flat design image into editable layers and reproduce it bit-perfect, returning the fidelity score

READ 2 tools

Read autodetect Auto-detect the elements (subjects and text) in a design image as relative bounding boxes. Returns: A JSON str Read diagnose Score how faithfully a reproduction matches an original (MAE / PSNR / exact-match % / stray px). Returns: A JS

FAQ

Questions about Reprise

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

The Reprise server is primarily read-only with 2 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 Reprise MCP server expose? +

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

How do I enforce a policy on Reprise? +

Register the Reprise 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 Reprise tool call.

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

ENFORCE POLICY ON REPRISE →

Instant setup, no code required.

3 Reprise tools catalogued and risk-classified — across an index of 46,500+ MCP servers.

// WHERE THIS COMES FROM

These policies come from Reprise's registry record.

The record behind this page: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.

Teams ship this data inside their own products. See what a licence covers →