# create_comment Comment on a post as the board team, optionally replying to a comment. Agent View of the PolicyLayer registry record for `create_comment`. HTML page: https://policylayer.com/tools/com-featurejet-feedback-board/create-comment ## Facts - Tool: `create_comment` - Server: FeatureJet (`https://mcp.featurejet.com/mcp`) — https://policylayer.com/tools/com-featurejet-feedback-board.md - Homepage: https://github.com/https://mcp.featurejet.com/mcp - Risk category: Write (Medium risk) - Registry record: grade F, identity unverified - Server auth posture: open - Server rate-limited: no - Parameters: 4 (3 required) - Recommended policy verdict: Rate-limited ## Parameters | Parameter | Type | Required | Description | | --- | --- | --- | --- | | `body` | string | yes | | | `slug` | string | yes | | | `post_id` | integer | yes | | | `parent_comment_id` | object | no | | Parameters from the server's own tool schema. ## Example call (MCP tools/call, JSON-RPC 2.0) ```json { "jsonrpc": "2.0", "id": 1, "method": "tools/call", "params": { "name": "create_comment", "arguments": { "body": "", "slug": "", "post_id": 0 } } } ``` ## Why create_comment is rated Medium This tool creates new content (a comment) without irreversible consequences, fits the Write category definition of 'creates or modifies data reversibly.' The blast radius is minimal since comments are typically non-destructive, user-facing feedback on a feedback board platform. Severity is low because misuse would result in unwanted comments rather than data loss or system compromise. From the tool's own definition: "Tool name 'create_comment' and description stating it comments 'on a post' indicates creation of new data (a comment). The description specifies it is a reversible action—commenting can be edited or deleted later." Risk signals: Accepts raw HTML/template content (body) ## Use case AI agents use create_comment to create or update resources in FeatureJet, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your FeatureJet environment. ## Recommended policy (PolicyLayer) Verdict: **Rate-limited**. Enforced by the PolicyLayer MCP gateway (https://policylayer.com/mcp-gateway) before a call reaches FeatureJet: ```json { "version": "1", "default": "deny", "tools": { "create_comment": { "limits": [ { "counter": "create_comment_rate", "window": "minute", "max": 30, "scope": "grant" } ] } } } ``` ## Other tools on FeatureJet (21) - `delete_post` — Destructive — https://policylayer.com/tools/com-featurejet-feedback-board/delete-post.md - `get_analytics` — Read — https://policylayer.com/tools/com-featurejet-feedback-board/get-analytics.md - `get_board` — Read — https://policylayer.com/tools/com-featurejet-feedback-board/get-board.md - `get_changelog` — Read — https://policylayer.com/tools/com-featurejet-feedback-board/get-changelog.md - `get_post` — Read — https://policylayer.com/tools/com-featurejet-feedback-board/get-post.md - `get_queue` — Read — https://policylayer.com/tools/com-featurejet-feedback-board/get-queue.md - `list_boards` — Read — https://policylayer.com/tools/com-featurejet-feedback-board/list-boards.md - `list_comments` — Read — https://policylayer.com/tools/com-featurejet-feedback-board/list-comments.md - `list_posts` — Read — https://policylayer.com/tools/com-featurejet-feedback-board/list-posts.md - `list_votes` — Read — https://policylayer.com/tools/com-featurejet-feedback-board/list-votes.md - `ping` — Read — https://policylayer.com/tools/com-featurejet-feedback-board/ping.md - `whoami` — Read — https://policylayer.com/tools/com-featurejet-feedback-board/whoami.md - `add_evidence` — Write — https://policylayer.com/tools/com-featurejet-feedback-board/add-evidence.md - `claim_post` — Write — https://policylayer.com/tools/com-featurejet-feedback-board/claim-post.md - `create_board` — Write — https://policylayer.com/tools/com-featurejet-feedback-board/create-board.md - `create_post` — Write — https://policylayer.com/tools/com-featurejet-feedback-board/create-post.md - `propose_status` — Write — https://policylayer.com/tools/com-featurejet-feedback-board/propose-status.md - `publish_board` — Write — https://policylayer.com/tools/com-featurejet-feedback-board/publish-board.md - `release_post` — Write — https://policylayer.com/tools/com-featurejet-feedback-board/release-post.md - `unpublish_board` — Write — https://policylayer.com/tools/com-featurejet-feedback-board/unpublish-board.md - `update_post` — Write — https://policylayer.com/tools/com-featurejet-feedback-board/update-post.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=com-featurejet-feedback-board · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/com-featurejet-feedback-board