# pr-comment

Adds, edits, or deletes a comment on a pull request. Returns structured data with the comment URL, operation type, comment ID, and body echo.

Agent View of the PolicyLayer registry record for `pr-comment`. HTML page: https://policylayer.com/tools/io-github-dave-london-http/pr-comment

## Facts

- Tool: `pr-comment`
- Server: Http (`@paretools/http`) — https://policylayer.com/tools/io-github-dave-london-http.md
- Install: `npx -y @paretools/http`
- Homepage: https://github.com/Dave-London/Pare
- Risk category: Write (Medium risk)
- Registry record: grade F, identity unverified
- Server rate-limited: no
- Parameters: 0
- Recommended policy verdict: Rate-limited

## Example call (MCP tools/call, JSON-RPC 2.0)

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "pr-comment",
    "arguments": {}
  }
}
```

## Why pr-comment is rated Medium

The tool modifies pull request comments (adds, edits, or deletes), which are reversible changes to data. While deletion is mentioned, the tool's primary function and name emphasize comment management rather than permanent destruction. The high severity reflects the potential for an AI agent to spam, defame, or manipulate PR discussions at scale, which could damage reputation or disrupt development workflows.

From the tool's own definition: "Tool description states it 'Adds, edits, or deletes a comment on a pull request' — core write operations that modify pull request state reversibly."

## Use case

AI agents use pr-comment to create or update resources in Http, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Http environment.

## Recommended policy (PolicyLayer)

Verdict: **Rate-limited**. Enforced by the PolicyLayer MCP gateway (https://policylayer.com/mcp-gateway) before a call reaches Http:

```json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "pr-comment": {
      "limits": [
        {
          "counter": "pr-comment_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}
```

## Other tools on Http (201)

- `branch` — Destructive — https://policylayer.com/tools/io-github-dave-london-http/branch.md
- `clean` — Destructive — https://policylayer.com/tools/io-github-dave-london-http/clean.md
- `compose-down` — Destructive — https://policylayer.com/tools/io-github-dave-london-http/compose-down.md
- `remove` — Destructive — https://policylayer.com/tools/io-github-dave-london-http/remove.md
- `reset` — Destructive — https://policylayer.com/tools/io-github-dave-london-http/reset.md
- `secret-delete` — Destructive — https://policylayer.com/tools/io-github-dave-london-http/secret-delete.md
- `tag` — Destructive — https://policylayer.com/tools/io-github-dave-london-http/tag.md
- `variable-delete` — Destructive — https://policylayer.com/tools/io-github-dave-london-http/variable-delete.md
- `workspace` — Destructive — https://policylayer.com/tools/io-github-dave-london-http/workspace.md
- `worktree` — Destructive — https://policylayer.com/tools/io-github-dave-london-http/worktree.md
- `add` — Execute — https://policylayer.com/tools/io-github-dave-london-http/add.md
- `add-package` — Execute — https://policylayer.com/tools/io-github-dave-london-http/add-package.md
- `ansible-galaxy` — Execute — https://policylayer.com/tools/io-github-dave-london-http/ansible-galaxy.md
- `ansible-playbook` — Execute — https://policylayer.com/tools/io-github-dave-london-http/ansible-playbook.md
- `api` — Execute — https://policylayer.com/tools/io-github-dave-london-http/api.md
- `apply` — Execute — https://policylayer.com/tools/io-github-dave-london-http/apply.md
- `audit` — Execute — https://policylayer.com/tools/io-github-dave-london-http/audit.md
- `bazel` — Execute — https://policylayer.com/tools/io-github-dave-london-http/bazel.md
- `biome-check` — Execute — https://policylayer.com/tools/io-github-dave-london-http/biome-check.md
- `bisect` — Execute — https://policylayer.com/tools/io-github-dave-london-http/bisect.md
- `black` — Execute — https://policylayer.com/tools/io-github-dave-london-http/black.md
- `build` — Execute — https://policylayer.com/tools/io-github-dave-london-http/build.md
- `bundle-exec` — Execute — https://policylayer.com/tools/io-github-dave-london-http/bundle-exec.md
- `bundle-install` — Execute — https://policylayer.com/tools/io-github-dave-london-http/bundle-install.md
- `check` — Execute — https://policylayer.com/tools/io-github-dave-london-http/check.md
- `cherry-pick` — Execute — https://policylayer.com/tools/io-github-dave-london-http/cherry-pick.md
- `clippy` — Execute — https://policylayer.com/tools/io-github-dave-london-http/clippy.md
- `cmake` — Execute — https://policylayer.com/tools/io-github-dave-london-http/cmake.md
- `compose-build` — Execute — https://policylayer.com/tools/io-github-dave-london-http/compose-build.md
- `compose-up` — Execute — https://policylayer.com/tools/io-github-dave-london-http/compose-up.md
- …and 171 more: https://policylayer.com/tools/io-github-dave-london-http.md

## For agents

This record is a snapshot. Live verdicts and the full registry:

- Check every server in your MCP config at once: `npx -y policylayer stack`
- Vet a server before you add it: install the mcp-precheck skill — `npx skills add https://policylayer.com` (skill text: https://policylayer.com/skill.md)
- Query the registry over MCP: endpoint `https://api.policylayer.com/mcp` — tools `check_mcp_server`, `check_mcp_stack`, `check_tool`, `search_registry`, `get_change_events`

---

Source: the PolicyLayer MCP registry — one continuously verified record per MCP server. Full record: https://policylayer.com/registry?q=io-github-dave-london-http · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/io-github-dave-london-http