Skip to main content
Glama

Proof Holdings

by holdings.proof
OverviewDiscussionsAdmin

start_2fa

Start a two-factor authentication challenge for a sensitive operation. Sends a verification code via the chosen channel. Returns a session ID, and for messaging channels: deep_link, qr_code (base64 PNG), and qr_text (UTF-8 text QR for terminal display).

Agent usage — full 2FA flow: (1) Call start_2fa with the appropriate action_type and channel. (2) Present the challenge, and do NOT announce a message the server did not send: email is the ONLY channel it dispatches on. On telegram/whatsapp the user opens deep_link and sends the message themselves; on sms they send sms_message to a number from sms_dids; the response's own instructions field says which. On email, a 200 carrying requires_email_selection: true and available_emails means nothing was sent and no session exists — ask which address and call again with email_id. For telegram/whatsapp, pass deep_link to render_auth_link; for sms, show sms_message. Never hand qr_text to a link renderer — it is the link already rendered as QR art, so print it verbatim inside a fenced code block only when a real terminal needs the QR. (3) Poll get_2fa_status with the returned session_id until status is "verified" (the user enters the code on their device) or "expired". (4) If verified, proceed with the protected operation (e.g. create_api_key). If expired, inform the user and offer to restart. Typical channels: "telegram" or "email". For email, the user may receive a magic link instead of a code — the backend handles this automatically.

The user does not see tool results — most clients fold them away, render_auth_link's output included. Before you wait or poll, put what the user must act on into your own reply text: the link itself (not a sentence announcing it), the SMS text and number, or a note to check their inbox.

ACCESS: needs a Proof account. Authenticate this client (Claude Code: /mcp → Authenticate), or sign in with start_login — a session opens this tool — then call this tool again.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
channelYesChannel to receive the verification code
targetsNoThe ids the step-up is FOR — the grant is bound to exactly these and refused for any other request (`reason: target_mismatch`). revocation_bulk: the asset id you will pass to revoke_asset (one code per asset); phone_remove / email_remove: the phone or email record id; domain_remove: the domain id; profile_delete: the project id; account_delete: your own user id (get_current_user). Leave out for the other action types.
email_idNoSpecific email ID for email channel (optional)
action_typeYesThe sensitive action requiring 2FA

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • changedInput schema / properties / action_type / enum
      Previous value: -[
-  "api_key_view",
-  "api_key_create",
-  "api_key_revoke",
-  "api_key_regenerate",
-  "phone_add",
-  "phone_remove",
-  "email_add",
-  "email_remove",
-  "account_delete"
-]New value: +[
+  "api_key_view",
+  "api_key_create",
+  "api_key_revoke",
+  "api_key_regenerate",
+  "phone_add",
+  "phone_remove",
+  "email_add",
+  "email_remove",
+  "account_delete",
+  "revocation_bulk",
+  "domain_remove",
+  "profile_delete",
+  "phone_primary",
+  "email_primary"
+]
    • addedInput schema / properties / targets
      Added value: +{
+  "description": "The ids the step-up is FOR — the grant is bound to exactly these and refused for any other request (`reason: target_mismatch`). revocation_bulk: the asset id you will pass to revoke_asset (one code per asset); phone_remove / email_remove: the phone or email record id; domain_remove: the domain id; profile_delete: the project id; account_delete: your own user id (get_current_user). Leave out for the other action types.",
+  "items": {
+    "maxLength": 256,
+    "minLength": 1,
+    "type": "string"
+  },
+  "maxItems": 25,
+  "minItems": 1,
+  "type": "array"
+}
  2. First observed

TDQS

A4.5/5.0
Behavior5/5

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

Annotations only say readOnlyHint=false and destructiveHint=false; the description goes far beyond by disclosing that email is the ONLY channel the server dispatches on, that telegram/whatsapp/sms require the user to send the message themselves, the requires_email_selection no-session case, the target binding/`target_mismatch` refusal, session expiry, and the Proof account/start_login auth prerequisite. That is exactly the behavioral context annotations cannot carry.

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?

The definition is long but front-loaded: the first sentence is a self-contained purpose statement, followed by the flow, the channel caveats, and the auth prerequisite. Nearly every sentence carries actionable instruction with no filler, though the volume is heavier than most agents need in a single description.

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?

There is no output schema, so the description must cover return values, and it does: session_id, deep_link, qr_code, qr_text, instructions, requires_email_selection, available_emails, sms_message/sms_dids. Combined with the polling guidance and auth requirement, an agent has everything needed to call and follow through.

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

Parameters4/5

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

Schema coverage is 100% and the schema descriptions for channel, action_type, targets and email_id are themselves detailed, so the baseline is 3. The description adds real meaning on top: which channels are typical, when email_id matters (after requires_email_selection), and how deep_link/sms_message map to render_auth_link, which the schema does not explain.

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

Purpose4/5

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

The opening states a specific verb and resource: it starts a 2FA challenge for a sensitive operation, sends a code over the chosen channel, and returns a session ID. It further pins down its position in the flow (start -> poll get_2fa_status -> proceed) which separates it from verify_2fa, get_2fa_status and wait_for_2fa. It never addresses the very similarly named sibling start_2fa_for_action, so sibling differentiation is incomplete.

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?

It gives an explicit numbered when-to-use sequence, names the follow-up tools (get_2fa_status, render_auth_link, create_api_key) and the branch conditions (verified vs expired, requires_email_selection). It also states typical channels and warns against misusing qr_text with a link renderer. Nothing about when to choose this tool over alternatives is left to inference.

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

All Proof Holdings toolsInspect
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.

Resources