@proof-holdings/mcp-server

Official

Overview Schema Source Related Servers Discussions Admin

create_confirmation

Sends an encrypted human-in-the-loop approval request to configured channels, with the first response deciding the outcome.

Instructions

Create a HITL confirmation request. Sends an approval request to the channels configured on the referenced HITL config. First response wins.

Agent usage: The HITL config referenced by hitl_id must be authorized before you can create confirmations. If this returns a 403 or "not authorized" error, call request_hitl_authorization on the HITL config first, then wait for the user to approve via the messaging channel. After creating a confirmation, poll get_confirmation to check for approval/denial, or, if the user (the HITL config owner) will decide it themselves, use get_confirmation_approval_link for their own approval link.

Encryption is NOT optional: a HITL config cannot send confirmations without a keypair, the human approves by decrypting in their browser, and message must be a JSON ciphertext envelope. Plaintext is refused with 400 message_not_encrypted; an envelope sealed to another key with 400 message_key_mismatch. Choose the version by who must be able to decrypt:

v1 (single-recipient): wraps the content key for the config owner only. Use ONLY when there are no enrolled non-owner approvers — with approvers enrolled it is refused with 400 envelope_missing_approvers.
v2 (multi-recipient): additionally wraps the content key for each enrolled approver via an approver_ek map, so every approver can decrypt. Build it with the SDK encryptMessageV2(plaintext, ownerPublicKey, hitlId, approverKeys) after fetching the approvers via the SDK getApproverKeys(hitlId) (GET /api/v1/hitl/:id/approver-keys). AAD is the hitlId.

ACCESS: needs a Proof account. Set PROOF_API_KEY and restart this server, then call this tool again. start_login does NOT open this tool.

Input Schema

Name	Required	Description
`hitl_id`	Yes	HITL config ID whose channels will receive the approval request
`message`	Yes	The client-encrypted ciphertext envelope as a JSON string (v1 or v2) — NOT the human-readable text. Encrypt the sentence the approver should read; passing it directly is refused with 400 `message_not_encrypted`, because the approval page can only decrypt an envelope.
`proof_expiry_days`	No	Per-request proof expiry override in days (7, 30, 90, or 365)

Output Schema

Name	Required	Description
`id`	No	MongoDB ObjectId
`status`	No	Status of a confirmation request. A confirmation that times out is `denied`, with `response.channel` `system` and `response.text` `timeout`.
`hitl_id`	No
`message`	No	The stored ciphertext envelope, echoed back verbatim. The server never sees the plaintext, so this is never the human sentence — the approver decrypts it in their browser.
`resends`	No	Every "Send again" (`POST /confirmations/{id}/resend`), oldest first, the last 50 kept. Absent from an API that predates it.
`response`	No	The decision and its evidence (null while pending)
`created_at`	No
`timeout_at`	No	When this confirmation will time out
`updated_at`	No
`proof_token`	No	Signed proof of the decision, approval or denial alike, naming who decided (`decided_by`, plus `authorization_id` for an approver); null while pending and for a system denial (`response.channel` is `system`)
`resolved_at`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed4 schema fields changedv1.7.2Nov 6, 2026

removedInput schema / additionalProperties
```
Removed value: -false
```
addedInput schema / properties / proof_expiry_days / maximum
```
Added value: +9007199254740991
```
addedInput schema / properties / proof_expiry_days / minimum
```
Added value: +-9007199254740991
```

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "$schema": "http://json-schema.org/draft-07/schema#",
+  "additionalProperties": {},
+  "properties": {
+    "created_at": {},
+    "hitl_id": {},
+    "id": {
+      "description": "MongoDB ObjectId"
+    },
+    "message": {
+      "description": "The stored ciphertext envelope, echoed back verbatim. The server never sees the plaintext, so this is never the human sentence — the approver decrypts it in their browser."
+    },
+    "proof_token": {
+      "description": "Signed proof of the decision, approval or denial alike, naming who decided (`decided_by`, plus `authorization_id` for an approver); null while pending and for a system denial (`response.channel` is `system`)"
+    },
+    "resends": {
+      "description": "Every \"Send again\" (`POST /confirmations/{id}/resend`), oldest first, the last 50 kept. Absent from an API that predates it."
+    },
+    "resolved_at": {},
+    "response": {
+      "description": "The decision and its evidence (null while pending)"
+    },
+    "status": {
+      "description": "Status of a confirmation request. A confirmation that times out is `denied`, with `response.channel` `system` and `response.text` `timeout`."
+    },
+    "timeout_at": {
+      "description": "When this confirmation will time out"
+    },
+    "updated_at": {}
+  },
+  "type": "object"
+}

Changed2 schema fields changedv1.6.0Oct 16, 2026

changedInput schema / properties / message / description

Previous value: -"Human-readable description of what needs approval"New value: +"The client-encrypted ciphertext envelope as a JSON string (v1 or v2) — NOT the human-readable text. Encrypt the sentence the approver should read; passing it directly is refused with 400 `message_not_encrypted`, because the approval page can only decrypt an envelope."

changedInput schema / properties / message / maxLength
```
Previous value: -2000New value: +10000
```

First observedv1.1.0Sep 9, 2026

TDQS

A4.9/5.0

Behavior5/5

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

Annotations only declare read=false/destructive=false, so the description carries the rest and does it thoroughly: the request fans out to configured channels, the first response wins, encryption is mandatory, and specific 400 error codes (message_not_encrypted, message_key_mismatch, envelope_missing_approvers) are documented. It also discloses the access precondition (PROOF_API_KEY required, start_login will not help), which is non-obvious failure-mode information.

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

Conciseness4/5

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

Front-loaded with the purpose sentence, then grouped into usage, then encryption rules — logical for a multi-step tool. It is long, and the plaintext-refusal error code is stated both in the description body and again in the message schema, so a small amount of text is duplicated rather than additive.

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 mutation tool with an output schema and three documented parameters, the definition covers everything an agent needs before calling: authorization prerequisite, envelope construction, failure signals, and the two routes for checking the outcome. Return values are correctly left to the output schema.

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

Parameters5/5

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

Schema coverage is 100%, so the baseline would be 3, but the description adds substantial meaning beyond it: it explains the v1 vs v2 envelope choice by 'who must be able to decrypt', the enrolled-approver rule that makes v1 fail, the approver_ek map, and the SDK helpers encryptMessageV2/getApproverKeys with the AAD being hitlId. That is decision-relevant construction guidance not present in the schema.

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?

Opens with a specific verb+resource: 'Create a HITL confirmation request' and immediately explains the effect — an approval request is broadcast to the channels on the referenced HITL config, with 'First response wins' as the resolution rule. This clearly distinguishes it from siblings like get_confirmation, wait_for_confirmation, and create_verification_request.

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?

Explicit 'Agent usage' block states the prerequisite (hitl_id must be authorized), the recovery path on 403 (call request_hitl_authorization then wait for channel approval), and names both follow-up alternatives — get_confirmation for polling and get_confirmation_approval_link when the config owner decides themselves — with the condition that selects each.

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

Deploy Server