add_evidence
Attach implementation evidence to a post (shown publicly). kind is one of branch|commit|pr|transcript|url; ref is the branch name, commit sha, or URL. Voters see these in the post page's "Implementation" section.
This record as markdown: /tools/com-featurejet-feedback-board/add-evidence.md
What add_evidence does on FeatureJet
AI agents use add_evidence 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.
| Parameter | Type | Required | Description |
|---|---|---|---|
ref | string | Yes | |
kind | string | Yes | |
slug | string | Yes | |
label | object | — | |
post_id | integer | Yes | |
action_key | object | — |
Parameters from the server's own tool schema.
Why add_evidence is rated Medium
This tool creates or modifies data reversibly by attaching evidence artifacts (branch, commit, PR, transcript, URL references) to existing posts. It does not delete, execute arbitrary code, move money, or trigger external operations—it only annotates posts with metadata.
From the tool's definition Tool attaches and modifies post data by adding implementation evidence; description states it shows evidence 'publicly' indicating the attachment creates or modifies post content that is visible to users.
Attacks that exploit this kind of access
The rule that runs add_evidence safely
PolicyLayer is an MCP gateway: it sits between your AI agents and FeatureJet, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For add_evidence, this is the rule to start with:
add_evidence stays usable, but capped: an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect FeatureJet, apply this rule, and every add_evidence call is checked against it from then on.
Questions about add_evidence
Attach implementation evidence to a post (shown publicly). kind is one of branch|commit|pr|transcript|url; ref is the branch name, commit sha, or URL. Voters see these in the post page's "Implementation" section. It is categorised as a Write tool in the FeatureJet MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
add_evidence accepts 6 parameters: ref, kind, slug, label, post_id, action_key. Required: ref, kind, slug, post_id. The full parameter table on this page comes from the server's own tool schema.
Register the FeatureJet MCP server in PolicyLayer and add a rule for add_evidence: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches FeatureJet. Nothing to install.
add_evidence is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the add_evidence rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for add_evidence. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
add_evidence is provided by the FeatureJet MCP server (https://mcp.featurejet.com/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on FeatureJet, and thousands of servers like it.
This server
Across the catalogue