Agent Receipts vs Proof Layer

A side-by-side look at the Agent Receipts and Proof Layer MCP servers: transport, auth, tools, quality signals, and the config to install either one in Claude, Cursor, Windsurf or VS Code.

A
Agent ReceiptsCryptography
Issue & verify signed (ed25519), hash-chained, timestamped provenance receipts for agent actions.37FairAuth: not declared
Proof Layer logoProof LayerCryptography · Local subprocess (stdio)Signed, hash-chained provenance receipts for AI agent actions.55GoodAuth: not declared

Verdict: choose Agent Receipts for cryptography work; choose Proof Layer for cryptography as a local process. You can also run both side by side in one mcpServers block.

Which MCP server should you choose?

A
Choose Agent Receipts when

  • You need dedicated capabilities in the Cryptography domain.
Explore Agent Receipts

Proof Layer logoChoose Proof Layer when

  • You need dedicated capabilities in the Cryptography domain.
  • You prefer a local stdio subprocess transport.
  • You have the keys it needs: PROOF_LAYER_API_KEY, PROOF_LAYER_API_URL.
  • You want tools like pl_evaluate, pl_get_receipt, pl_verify_receipt.
Explore Proof Layer

Feature & specification comparison

Rows where the two servers differ are marked.

Spec
A
Agent Receipts
Proof Layer logoProof Layer
CategoryCryptographyCryptography
Quality signal37/100 · Fair55/100 · Good
Install commandNot confirmed yetConfirmed
Transport—Local subprocess (stdio)
AuthNot declaredNot declared
PricingNot declaredNot declared
Required env varsNone listedPROOF_LAYER_API_KEYPROOF_LAYER_API_URL
Verified ownerCommunity listingCommunity listing
GitHub stars—0
Directory activity 2 views 0 installs 0 upvotes 2 views 0 installs 0 upvotes
ToolsNot listed8

Tools & capabilities

Agent Receipts tools

No tool names declared yet. Check the project README from the listing page.

Proof Layer tools 8

  • pl_evaluateSubmit an AI agent action proposal to Proof Layer for governance evaluation. Returns a cryptographically-signed receipt with a verdict of EXECUTE, BLOCK, REVIEW, or SHADOW. Use this before any consequential agent action (sending emails, modifying data, making payments, etc.).
  • pl_get_receiptRetrieve a Proof Layer audit receipt by its UUID. Returns the full receipt including verdict, signature, and policy pack hash.
  • pl_verify_receiptCryptographically verify a Proof Layer receipt. Checks the Ed25519 signature and confirms the signing key is ACTIVE. Returns valid: true/false with a reason.
  • pl_list_receiptsList recent Proof Layer audit receipts for the authenticated tenant. Supports filtering by agent and verdict.
  • pl_usageGet current Proof Layer quota usage — receipts used, receipts remaining, credit balance, billing cycle dates, and plan tier.
  • pl_list_policy_packsList all governance policy packs for the authenticated tenant, including which one is currently active.
  • pl_create_planA human approves a governed plan — a scoped, time-bounded set of future actions across named agents. Returns a plan_id and JTI that agents use to request delegation receipts via pl_delegate. Scope patterns support wildcards: 'build:*' authorizes any action starting with 'build:'.
  • pl_delegateAn agent requests authorization to perform a specific action under a parent plan. Returns 'ok' with a signed receipt (proceed with the action), 'checkpoint_required' (human must re-approve this specific action), or 'denied' (agent or action not authorized under the plan).

Ready-to-paste client configs

Paste either block (or both) into your client config, e.g. claude_desktop_config.json or ~/.cursor/mcp.json. We only show a config when the install command is confirmed.

Agent Receipts

No confirmed install command for Agent Receipts yet — follow the setup steps linked from its listing page rather than a guessed package name.

Proof Layer

mcpServers (Claude Desktop / Cursor)
{
  "mcpServers": {
    "proof-layer": {
      "command": "npx",
      "args": [
        "-y",
        "@proof-layer/mcp@latest"
      ],
      "env": {
        "PROOF_LAYER_API_KEY": "YOUR_PROOF_LAYER_API_KEY_HERE",
        "PROOF_LAYER_API_URL": "YOUR_PROOF_LAYER_API_URL_HERE"
      }
    }
  }
}

Frequently asked questions

Agent Receipts is categorized under Cryptography and uses an install path we have not confirmed yet. Proof Layer belongs to Cryptography and uses a local stdio subprocess. Pick Agent Receipts for cryptography work and Proof Layer for cryptography.

Copy the mcpServers block from the config section on this page into your client's config (for example claude_desktop_config.json or ~/.cursor/mcp.json), then fully restart the client. Agent Receipts has no confirmed install command yet — follow its own setup instructions.

Agent Receipts has no declared pricing — check the project's own site. Proof Layer has no declared pricing — check the project's own site. If a server needs environment variables such as API keys, define them under the env key in your client's MCP config.

Yes. MCP clients support multiple servers: add agent-receipts and proof-layer as separate keys in the same mcpServers object, and your assistant will call tools from either one.

On AllMCPs, Agent Receipts has a quality signal of 37/100 (Fair) with 2 views, 0 installs and 0 GitHub stars. Proof Layer has 55/100 (Good) with 2 views, 0 installs and 0 GitHub stars.