excalibur-mcp

excalibur_request_npub_proof

Request npub ownership proof from a patron via Nostr DM.

This is the npub-OWNERSHIP-PROOF flow — use it when a call returns proof_required. It proves the caller controls an npub; it does NOT deliver any service secret. To hand an operator its API keys or OAuth secrets, use request_credential_channel instead.

Sends a challenge DM that the patron must sign and reply to using their Nostr client. This is a human-in-the-loop flow.

After calling this tool, STOP and tell the user to check their Nostr client and reply to the challenge. Wait for the user to confirm they have replied before calling receive_npub_proof. Do NOT poll or retry — each receive_npub_proof call destructively drains the relay mailbox.

Returns a dpop_token — the one-time challenge nonce shown in the DM. Pass it to receive_npub_proof to collect the reply. It is a matching token, not a credential: on its own it authorizes nothing.

Lifecycle: receive_npub_proof returns the proof grant, which expires after the duration the patron named in their reply. When it expires, call request_npub_proof again for a fresh challenge, then wait for the user, then call receive_npub_proof.

Free.

Input Schema

TableJSON Schema

Name	Required	Description
`reason`	No	Optional. A human-readable purpose for the request ("I'm working on your request XYZ and need the Operator to do ABC for you"). Signed into the provenance attestation and shown in the DM, so the recipient sees why they are being asked — especially useful when the signer is unknown to them.
`verify_at`	No	Optional. A free-form statement of WHERE you (the initiating agent) already showed this proof's one-time code to the user — a URL, or "your Claude.ai conversation", "the Grok session". The OAuth 2.0 Device Grant ``verification_uri``, generalized: the user approves only if the code in the DM matches the one you displayed there, so an unsolicited request they've never seen is refused. Signed into the attestation.
`patron_npub`	No	Required. The patron's npub to request proof from.

Output Schema

TableJSON Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

Changed3 schema fields changedAug 17, 2026

addedInput schema / properties / patron_npub / description

Added value: +"Required. The patron's npub to request proof from."

addedInput schema / properties / reason / description

Added value: +"Optional. A human-readable purpose for the request\n(\"I'm working on your request XYZ and need the Operator to do\nABC for you\"). Signed into the provenance attestation and shown\nin the DM, so the recipient sees *why* they are being asked —\nespecially useful when the signer is unknown to them."

addedInput schema / properties / verify_at / description

Added value: +"Optional. A free-form statement of WHERE you (the\ninitiating agent) already showed this proof's one-time code to\nthe user — a URL, or \"your Claude.ai conversation\", \"the Grok\nsession\". The OAuth 2.0 Device Grant ``verification_uri``,\ngeneralized: the user approves only if the code in the DM matches\nthe one you displayed there, so an unsolicited request they've\nnever seen is refused. Signed into the attestation."

Changed2 schema fields changedJul 21, 2026
- addedInput schema / properties / reason
```
Added value: +{
+  "default": "",
+  "type": "string"
+}
```
- addedInput schema / properties / verify_at
```
Added value: +{
+  "default": "",
+  "type": "string"
+}
```
First observedJul 16, 2026

TDQS

A4.7/5.0

Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full burden and does so richly: it flags a human-in-the-loop flow, warns that receive_npub_proof destructively drains the relay mailbox (do NOT poll), explains the dpop_token is a matching nonce that authorizes nothing on its own, and describes the expiry/re-request lifecycle.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Despite its length it is front-loaded and sectioned (Returns, Lifecycle, bolded warnings), and each sentence carries non-redundant operational guidance. The critical routing and stopping instructions appear before the details.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a multi-step, human-gated flow with no annotations, this is complete: it covers prerequisites, the stop/wait behavior, the token handoff, and the expiry-recovery loop. An output schema exists, yet the description still usefully clarifies what the return token is and is not.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the schema already documents reason, verify_at, and patron_npub in detail. The description body adds no parameter-level meaning beyond the schema, so the baseline of 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The first sentence names a specific verb (request), resource (npub ownership proof), and channel (Nostr DM). It explicitly separates itself from the sibling request_credential_channel by stating it does NOT deliver service secrets, so an agent can distinguish the two without opening either schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

States exactly when to use it ('when a call returns proof_required') and when not ("To hand an operator its API keys or OAuth secrets, use request_credential_channel instead"). Adds an explicit no-poll/no-retry rule and instructs the agent to stop and wait for user confirmation.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All excalibur-mcp tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.