Skip to main content
Glama
Sign In

Provian

by ai.provian
OverviewDiscussionsAdmin

recovery_escrow

Recovery escrow: escrow a copy of your wallet key that only your human's phone can open, so your linked human can restore your key if your runtime or key is lost. It never holds earnings: your mints and payouts go ahead either way. Call it right after wallet_create when that call did not escrow (its recovery says why), or after you link. REMOTE: seal your private key IN YOUR OWN RUNTIME to recovery_anchor_pubkey (from wallet_challenge, wallet_create or escrow_target) and pass only the result: sealed_key_blob = base64url-nopad(0x01 || eph_pub || XChaCha20-Poly1305(key, nonce, aad, privkey)), X25519 eph_pub/eph_secret, shared = X25519(eph_secret, anchor), key‖nonce = HKDF-SHA256(shared, salt=eph_pub‖anchor, info="provian-agent-recovery-v1", 56 bytes), aad = 0x01‖anchor (full recipe in recovery_seal). Never send the key. LOCAL stdio: omit sealed_key_blob and it seals in-process with your local key (read from escrow_target when no anchor is given). The relay accepts only an anchor it names for you (your birth anchor or your linked human's published anchor) and refuses any other with recovery_anchor_not_recognized. Requires your agent API credential.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "wallet_id": "<wallet_id>"
    },
    "name": "recovery_escrow"
  }
}

Input Schema

NameRequiredDescriptionDefault
wallet_idYesYour agent wallet id (wallet_aw_…).
sealed_key_blobNoYour key sealed to that anchor (base64url ciphertext). Local mode: omit to seal in-process.
recovery_anchor_pubkeyNoThe anchor you sealed to (43 base64url characters). Local mode: optional.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.5/5.0
Behavior5/5

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

No annotations exist, so the description carries the full burden and does so: it discloses the credential requirement ('Requires your agent API credential'), the relay's anchor allow-list policy and its failure mode ('recovery_anchor_not_recognized'), the security invariant ('Never send the key'), and the distinct remote-vs-local sealing behaviors. That is exactly the behavioral context an agent needs before invoking a key-material operation.

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

Conciseness3/5

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

Purpose and behavior are front-loaded, but the body is a dense wall of crypto recipe text embedded mid-sentence, including a construction the description itself points to as living in recovery_seal ('full recipe in recovery_seal'), which is partly duplicative. Most sentences are load-bearing, though the formatting makes it harder to scan than it needs to be.

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

Completeness4/5

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

For a high-stakes key-escrow call the description covers inputs, modes, auth, and failure modes thoroughly. It never describes what a successful call returns (e.g., any escrow confirmation or anchor attestation), and there is no output schema to fall back on, so the agent must infer the response shape.

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 is 3, but the description goes far beyond it: it specifies the exact byte layout and cipher suite for sealed_key_blob (0x01 prefix, eph_pub, XChaCha20-Poly1305, HKDF info string, AAD), where recovery_anchor_pubkey comes from, and that sealed_key_blob must be omitted in local stdio mode. This is genuine added meaning, not restatement.

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?

States a specific verb and resource ('escrow a copy of your wallet key') and immediately bounds the scope by saying what it is not ('It never holds earnings: your mints and payouts go ahead either way'), which separates it from the payment/escrow siblings in the list. An agent can tell what this does without opening the schema.

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

Usage Guidelines4/5

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

Gives concrete trigger conditions: 'right after wallet_create when that call did not escrow (its `recovery` says why), or after you link.' That implies when not to call (wallet_create already escrowed) and routes to escrow_target/wallet_challenge as the source of the anchor. It does not spell out re-escrow/rotation or key-replacement cases, so it is clear context rather than an exhaustive when/when-not map.

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

All Provian 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