// SCAN REPORT

Downscoping

15 tools. 11 can modify or destroy data without limits.

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

Last updated: 3 Jul 2026

11 can modify or destroy data

4 read-only

15 tools total

Community server · catalogue entry verified 03/07/2026

How to control Downscoping ↓

TOOL MAP

What Downscoping exposes to your agents

Read (4) Write / Execute (11) Destructive / Financial (0)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

High Risk

The most dangerous Downscoping tools

Write · Medium add_inline_pr_comment This tool writes comment data to a pull request, which is reversible (comments can be edited or deleted). Write · Medium add_pr_comments This tool creates new data (a PR comment) and modifies the pull request by appending content. Write · Medium create_issue This tool creates new data (a GitHub issue) which is a reversible write operation. Write · Medium create_pr This tool creates new data (a pull request) in a repository, which is a reversible modification.

11 of Downscoping's 15 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Downscoping

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

Rate limit write operations

{
  "add_inline_pr_comment": {
    "limits": [
      {
        "counter": "add_inline_pr_comment_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "get_latest_sha": {
    "limits": [
      {
        "counter": "get_latest_sha_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 Downscoping — 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 DOWNSCOPING →

Instant setup, no code required.

FULL CATALOGUE

All 15 Downscoping tools

WRITE 11 tools

Write add_inline_pr_comment Add an inline review comment to a file line within a pull request. Write add_pr_comments Add a comment to a specific pull request. Write create_issue Create a new issue in a GitHub repository. Write create_pr Create a new pull request. Write create_release Create a new release in a GitHub repository. Write create_tag Create a new tag in a GitHub repository. Write merge_pr Merge a pull request. Write update_assignees Update assignees for an issue or pull request. Write update_issue Update an existing issue. Write update_pr_description Update the title and description of a pull request. Write update_reviews Submit a review for a pull request.

READ 4 tools

Read get_latest_sha Fetch the SHA of the latest commit. Read get_pr_content Fetch the content/details of a specific pull request. Read get_pr_diff Fetch the diff/patch of a specific pull request. Read list_open_issues_prs List open pull requests or issues for a repository owner.

FAQ

Questions about Downscoping

How do I prevent bulk modifications through Downscoping? +

The Downscoping server has 11 write tools including add_inline_pr_comment, add_pr_comments, create_issue. Set a rate limit in your policy -- for example, 10 calls per hour prevents an agent from making more than 10 modifications per hour. PolicyLayer enforces this at the gateway, before calls reach Downscoping.

How many tools does the Downscoping MCP server expose? +

15 tools across 2 categories: Read, Write. 4 are read-only. 11 can modify, create, or delete data.

How do I enforce a policy on Downscoping? +

Register the Downscoping 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 Downscoping tool call.

Deterministic rules across all 15 Downscoping tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON DOWNSCOPING →

Instant setup, no code required.

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