// SCAN REPORT

FeatureJet

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

1 destructive tool with no built-in limits. Policy required.

Last updated: 5 Aug 2026

11 can modify or destroy data

11 read-only

22 tools total

Community server · catalogue entry checked 05/08/2026 · full schemas captured for 19 of 22 tools

How to control FeatureJet ↓

TOOL MAP

What FeatureJet exposes to your agents

Read (11) Write / Execute (10) Destructive / Financial (1)

Running more than one server? Check your whole stack →

CONTEXT-WINDOW COST

What FeatureJet costs in tokens

2,304 tokens of tool definitions, loaded on every request

1.2% of a 200k context window

213 heaviest tool: update_post

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

MOST DANGEROUS TOOLS

Critical Risk

The most dangerous FeatureJet tools

Destructive · High delete_post This tool permanently removes or hides a post from the feedback board, which cannot be undone. Write · High unpublish_board Unpublishing a board makes it inaccessible publicly, but is reversible by republishing. Write · High publish_board This tool creates a public-facing change by making a previously private or unpublished board accessible at its public URL. Write · Medium add_evidence This tool creates or modifies data reversibly by attaching evidence artifacts (branch, commit, PR, transcript, URL references) to existing posts.

11 of FeatureJet's 22 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control FeatureJet

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

Deny destructive operations

{
  "delete_post": {
    "deny_if": [
      {
        "conditions": [],
        "on_deny": "Blocked by default. Requires approval."
      }
    ]
  }
}

Destructive tools should never be available to autonomous agents without human approval.

Rate limit write operations

{
  "add_evidence": {
    "limits": [
      {
        "counter": "add_evidence_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "get_analytics": {
    "limits": [
      {
        "counter": "get_analytics_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 FeatureJet — 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 FEATUREJET →

Instant setup, no code required.

FULL CATALOGUE

All 22 FeatureJet tools

DESTRUCTIVE 1 tools

Destructive delete_post Delete a post by hiding it through the developer API.

WRITE 10 tools

Write add_evidence Attach implementation evidence to a post (shown publicly). kind is one of branch|commit|pr|transcript Write claim_post Atomically claim a post before working on it (double-work guard). ttl_seconds defaults to 3600 (max 8 Write create_board Create a new feedback board, as a DRAFT. slug is the board's URL path segment (lowercase, hyphenated, Write create_comment Comment on a post as the board team, optionally replying to a comment. Write create_post Create a post on a board. Write propose_status Propose a status change for the board owner to confirm. The agent-honest way to mark work done: nothi Write publish_board Publish a board so it is live at its public URL. OFF BY DEFAULT. Putting a board on the public intern Write release_post Release a post's claim so other agents can pick it up. Write unpublish_board Return a board to draft so its public URL stops serving it. Nothing is deleted; publish it again to b Write update_post Update mutable post fields; null queue_rank explicitly un-ranks.

READ 11 tools

Read get_analytics Get read-only analytics for a board. Read get_board Get one board by slug. Read get_changelog List shipped posts for a board. Read get_post Get one post by board slug and post id. Read get_queue Top UNCLAIMED posts in the owner's curated build order. Owner-ranked posts (queue_rank, lower = soone Read list_boards List boards available to the caller's FeatureJet API key. Read list_comments List comments for a post. Read list_posts List posts for a board, optionally filtered by status, search, or tag. Read list_votes List vote metadata for a post. Read ping Check MCP and FeatureJet API reachability for the caller's key. Read whoami Confirm the caller's API key by listing accessible boards.

EXPLORE

Related servers

Other MCP servers with similar tools — same risk classification, starter policies for each.

FAQ

Questions about FeatureJet

Can an AI agent delete data through the FeatureJet MCP server? +

Yes. The FeatureJet server exposes 1 destructive tools including delete_post. These permanently remove resources with no undo. PolicyLayer blocks destructive tools by default so they never reach the upstream server.

How do I prevent bulk modifications through FeatureJet? +

The FeatureJet server has 10 write tools including add_evidence, claim_post, create_board. 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 FeatureJet.

How many tools does the FeatureJet MCP server expose? +

22 tools across 3 categories: Destructive, Read, Write. 11 are read-only. 11 can modify, create, or delete data.

How do I enforce a policy on FeatureJet? +

Register the FeatureJet 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 FeatureJet tool call.

Deterministic rules across all 22 FeatureJet tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON FEATUREJET →

Instant setup, no code required.

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

// WHERE THIS COMES FROM

These policies come from FeatureJet'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 →