get_evidence_pack

Retrieve Evidence Pack metadata for an existing lock. Returns the 19-file manifest, FRE 902(14) certification info, Bitcoin anchor details, and chain-of-custody log. Does not download the pack itself — that requires a $29 purchase via the web interface.

Server Unfakable unfakable/mcp
Category Read
Risk class Low
Parameters 00 required

What get_evidence_pack does on Unfakable

AI agents call get_evidence_pack to retrieve information from Unfakable without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

Why get_evidence_pack needs a policy

This tool retrieves and returns metadata about an existing lock—including manifest, certification info, and chain-of-custody logs. It is a read-only query operation that returns information without side effects. Although the Evidence Pack is associated with a $29 purchase, that transaction occurs separately via the web interface and is not triggered or executed by this tool.

From the tool's definition Tool description states it 'Retrieve[s] Evidence Pack metadata' and explicitly clarifies 'Does not download the pack itself.' The action is query/retrieval of metadata only with no modifications, deletions, or financial transactions initiated by the tool…

Questions about get_evidence_pack

What does the get_evidence_pack tool do? +

Retrieve Evidence Pack metadata for an existing lock. Returns the 19-file manifest, FRE 902(14) certification info, Bitcoin anchor details, and chain-of-custody log. Does not download the pack itself — that requires a $29 purchase via the web interface. It is categorised as a Read tool in the Unfakable MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on get_evidence_pack? +

Register the Unfakable MCP server in PolicyLayer and add a rule for get_evidence_pack: 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 Unfakable. Nothing to install.

What risk level is get_evidence_pack? +

get_evidence_pack is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit get_evidence_pack? +

Yes. Add a rate_limit block to the get_evidence_pack 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.

How do I block get_evidence_pack completely? +

Set action: deny in the PolicyLayer policy for get_evidence_pack. 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.

What MCP server provides get_evidence_pack? +

get_evidence_pack is provided by the Unfakable MCP server (unfakable/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

// LOOK UP ANOTHER SERVER

Every MCP server has a record like this.

Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.

Teams ship this data inside their own products. See what a licence covers →

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.