Signet

Make AI agent tool calls verifiable at the execution boundary
_{See which agent called which tool, when, and with what params hash. Verify offline or before execution in 3 lines.}

_{TypeScript packages:
@signet-auth/core ·
@signet-auth/mcp ·
@signet-auth/mcp-server ·
@signet-auth/mcp-tools ·
@signet-auth/vercel-ai}

AI agents can open tickets, call MCP tools, run shell commands, and ship code with almost no built-in accountability. Signet gives each agent an Ed25519 identity, signs every tool call, writes a hash-chained audit log, and lets clients or servers verify what was actually sent before trusting it.

If Signet is useful to you, star this repo to help more teams find it.

Start with the CLI flow below to see how Signet signs and audits a tool call. Then jump to See It Reject Bad Requests to watch the execution side block unsigned, tampered, stale, or mis-targeted requests before they run.

Signet demo

_{This first demo shows signing + audit receipts. See also the MCP flow diagram.}

Why Signet

Signet adds a lightweight trust layer for agent actions:

Sign every tool call with the agent's cryptographic key
Audit what happened with an append-only, hash-chained local log
Verify any action receipt offline, no network needed
Integrate with Claude Code, Codex CLI, MCP clients and servers, Python frameworks, and Vercel AI SDK

Try It In 30 Seconds

pip install signet-auth

from signet_auth import SigningAgent

agent = SigningAgent.create("my-agent", owner="team")
receipt = agent.sign("github_create_issue", params={"title": "fix bug"})

assert agent.verify(receipt)
print(receipt.id)

If you're new, start with one of these four paths:

Choose Your Path

Claude Code: Best for the fastest first run in a coding agent. Run signet claude install. In 5 minutes you'll have signed tool calls and a local audit log at ~/.signet/audit/.
Codex CLI: Best for signing Bash tool calls in Codex. Copy plugins/codex/ into ~/.codex/plugins/signet and add one PostToolUse hook. In 5 minutes you'll have signed Bash actions in Codex using the same audit trail.
MCP clients: Best if you control an MCP client or transport. Wrap your transport with new SigningTransport(inner, secretKey, "my-agent"). In 5 minutes you'll have signed tools/call requests with receipts in params._meta._signet.
MCP servers: Best if you want verification before execution. Call verifyRequest(request, {...}) in your tool handler. In 5 minutes you'll have signer, freshness, target-binding, and tool/params checks at the execution boundary.

See It Reject Bad Requests

Run the shortest execution-boundary demo:

cd examples/mcp-agent
npm run execution-boundary-demo

Execution-boundary demo showing invalid requests rejected before execution

_{Prefer motion? Watch the MP4 or GIF.}

See examples/mcp-agent/demo-execution-boundary.mjs for the demo source.

When Teams Reach For Signet

You need an audit trail for coding agents, MCP tools, or CI automation
You want to prove which agent requested an action after an incident
You need receipts that can be verified offline without depending on a hosted service
You want signed tool-call evidence without adding a proxy or gateway to your stack

What Signet Is And Isn't

Signet is an attestation layer for agent actions: sign, audit, and verify
Signet is designed to fit into existing agent stacks with SDKs, plugins, and MCP middleware
Signet is not a policy engine, firewall, or action blocker
Signet is not a replacement for gateways; it complements prevention and enforcement tools

Install

# CLI
cargo install signet-cli

# Python
pip install signet-auth

# TypeScript (MCP middleware)
npm install @signet-auth/core @signet-auth/mcp

# TypeScript (MCP server verification)
npm install @signet-auth/mcp-server

# TypeScript (Vercel AI SDK middleware)
npm install @signet-auth/vercel-ai

Quick Start

Claude Code Plugin

Auto-sign every tool call in Claude Code with zero configuration:

# From marketplace (if available)
claude plugin add signet

# Or from Git
claude plugin add --from https://github.com/Prismer-AI/signet

# Or via CLI
signet claude install

Every tool call is signed with Ed25519 and logged to a hash-chained audit trail at ~/.signet/audit/.

Alternative: add a hook directly to ~/.claude/settings.json without the plugin system:

{
  "hooks": {
    "PostToolUse": [{
      "matcher": "*",
      "hooks": [{
        "type": "command",
        "command": "node ~/signet/plugins/claude-code/bin/sign.cjs",
        "timeout": 5
      }]
    }]
  }
}

Codex Plugin

Auto-sign every Bash tool call in Codex CLI:

git clone https://github.com/Prismer-AI/signet.git
cp -r signet/plugins/codex ~/.codex/plugins/signet

Then add the hook to ~/.codex/hooks.json:

{
  "hooks": {
    "PostToolUse": [{
      "matcher": "Bash",
      "hooks": [{
        "type": "command",
        "command": "node \"$HOME/.codex/plugins/signet/bin/sign.cjs\"",
        "timeout": 5
      }]
    }]
  }
}

Or use the MCP server for on-demand signing tools:

codex mcp add signet -- npx @signet-auth/mcp-tools

CLI

# Generate an agent identity
signet identity generate --name my-agent

# Sign an action
signet sign --key my-agent --tool "github_create_issue" \
  --params '{"title":"fix bug"}' --target mcp://github.local

# Verify a receipt
signet verify receipt.json --pubkey my-agent

# Audit recent actions
signet audit --since 24h

# Verify log integrity
signet verify --chain

MCP Client Integration (TypeScript)

Signet MCP bilateral flow demo

import { Client } from "@modelcontextprotocol/sdk/client/index.js";
import { StdioClientTransport } from "@modelcontextprotocol/sdk/client/stdio.js";
import { generateKeypair } from "@signet-auth/core";
import { SigningTransport } from "@signet-auth/mcp";

// Generate an agent identity
const { secretKey } = generateKeypair();

// Wrap any MCP transport -- all tool calls are now signed
const inner = new StdioClientTransport({ command: "my-mcp-server" });
const transport = new SigningTransport(inner, secretKey, "my-agent");

const client = new Client({ name: "my-agent", version: "1.0" }, {});
await client.connect(transport);

// Every callTool() is now cryptographically signed
const result = await client.callTool({
  name: "echo",
  arguments: { message: "Hello!" },
});

Every tools/call request gets a signed receipt injected into params._meta._signet.

MCP Server Verification

If you control the MCP server too, verify requests before execution:

import { verifyRequest } from "@signet-auth/mcp-server";

server.setRequestHandler(CallToolRequestSchema, async (request) => {
  const verified = verifyRequest(request, {
    trustedKeys: ["ed25519:..."],
    maxAge: 300,
  });
  if (!verified.ok) return { content: [{ type: "text", text: verified.error }], isError: true };
  console.log(`Verified: ${verified.signerName}`);
  // process tool call...
});

Signet MCP end-to-end demo

Vercel AI SDK Integration

import { generateText } from "ai";
import { generateKeypair } from "@signet-auth/core";
import { createSignetCallbacks } from "@signet-auth/vercel-ai";

const { secretKey } = generateKeypair();
const callbacks = createSignetCallbacks(secretKey, "my-agent");

const result = await generateText({
  model: openai("gpt-4"),
  tools: { myTool },
  ...callbacks,
  prompt: "...",
});

// Every tool call is now signed
console.log(callbacks.receipts);

Reference MCP Server

This repo also includes a minimal MCP reference server that demonstrates server-side verification with @signet-auth/mcp-server.

cd examples/mcp-agent
npm ci
npm run verifier-server

Available tools:

inspect_current_request — verifies the current MCP tool call if it includes params._meta._signet
verify_receipt — verifies a raw Signet receipt against a public key
verify_request_payload — verifies a synthetic MCP tools/call payload offline

Environment variables:

SIGNET_TRUSTED_KEYS — comma-separated ed25519:<base64> public keys
SIGNET_REQUIRE_SIGNATURE — true or false (default false)
SIGNET_MAX_AGE — max receipt age in seconds (default 300)
SIGNET_EXPECTED_TARGET — optional expected receipt.action.target

Standalone MCP Signing Server

@signet-auth/mcp-tools exposes Signet signing, verification, and content hashing as MCP tools — plug into any MCP-compatible client:

npx @signet-auth/mcp-tools

Available tools: signet_generate_keypair, signet_sign, signet_verify, signet_content_hash.

Python (LangChain / CrewAI / AutoGen + 6 more)

pip install signet-auth

from signet_auth import SigningAgent

# Create an agent identity (saved to ~/.signet/keys/)
agent = SigningAgent.create("my-agent", owner="willamhou")

# Sign any tool call -- receipt is auto-appended to audit log
receipt = agent.sign("github_create_issue", params={"title": "fix bug"})

# Verify
assert agent.verify(receipt)

# Query audit log
for record in agent.audit_query(since="24h"):
    print(f"{record.receipt.ts} {record.receipt.action.tool}")

LangChain Integration

from signet_auth import SigningAgent
from signet_auth.langchain import SignetCallbackHandler

agent = SigningAgent("my-agent")
handler = SignetCallbackHandler(agent)

# Every tool call is now signed + audited
chain.invoke(input, config={"callbacks": [handler]})

# Async chains supported too
from signet_auth.langchain import AsyncSignetCallbackHandler

CrewAI Integration

from signet_auth import SigningAgent
from signet_auth.crewai import install_hooks

agent = SigningAgent("my-agent")
install_hooks(agent)

# All CrewAI tool calls are now globally signed
crew.kickoff()

AutoGen Integration

from signet_auth import SigningAgent
from signet_auth.autogen import signed_tool, sign_tools

agent = SigningAgent("my-agent")

# Wrap a single tool
wrapped = signed_tool(tool, agent)

# Or wrap all tools at once
wrapped_tools = sign_tools([tool1, tool2], agent)

LangGraph Integration

LangGraph uses LangChain's callback system — the same handler works directly:

from signet_auth import SigningAgent
from signet_auth.langgraph import SignetCallbackHandler

agent = SigningAgent("my-agent")
handler = SignetCallbackHandler(agent)

result = graph.invoke(input, config={"callbacks": [handler]})

LlamaIndex Integration

from signet_auth import SigningAgent
from signet_auth.llamaindex import install_handler

agent = SigningAgent("my-agent")
handler = install_handler(agent)

# All tool call events are now signed
index = ... # your LlamaIndex setup
response = index.as_query_engine().query("What is Signet?")

# Access receipts
print(handler.receipts)

Pydantic AI Integration

from signet_auth import SigningAgent
from signet_auth.pydantic_ai_integration import SignetCapability

agent = SigningAgent("my-agent")
capability = SignetCapability(agent)

pydantic_agent = Agent(model, capabilities=[capability])

Google ADK Integration

from signet_auth import SigningAgent
from signet_auth.google_adk import SignetPlugin

agent = SigningAgent("my-agent")
plugin = SignetPlugin(agent)

# Pass as callback to ADK agent

Smolagents Integration

from signet_auth import SigningAgent
from signet_auth.smolagents import signet_step_callback

agent = SigningAgent("my-agent")
callback = signet_step_callback(agent)

bot = CodeAgent(tools=[...], model=model, step_callbacks=[callback])

OpenAI Agents SDK Integration

from signet_auth import SigningAgent
from signet_auth.openai_agents import SignetAgentHooks

agent = SigningAgent("my-agent")

oai_agent = Agent(
    name="assistant",
    hooks=SignetAgentHooks(agent),
    tools=[...],
)

Note: Tool call arguments are not yet available in the hook API (issue #939). Only the tool name is signed.

Low-Level API

from signet_auth import generate_keypair, sign, verify, Action

kp = generate_keypair()
action = Action("github_create_issue", params={"title": "fix bug"})
receipt = sign(kp.secret_key, action, "my-agent", "willamhou")
assert verify(receipt, kp.public_key)

Bilateral Receipt (Server Co-signing)

from signet_auth import generate_keypair, sign, sign_bilateral, verify_bilateral, Action

# Agent signs the tool call
agent_kp = generate_keypair()
action = Action("github_create_issue", params={"title": "fix bug"})
agent_receipt = sign(agent_kp.secret_key, action, "my-agent")

# Server co-signs with the response
server_kp = generate_keypair()
bilateral = sign_bilateral(
    server_kp.secret_key, agent_receipt,
    {"content": [{"type": "text", "text": "issue #42 created"}]},
    "github-server",
)
assert verify_bilateral(bilateral, server_kp.public_key)
assert bilateral.v == 3  # v3 = bilateral receipt

How It Works

Your Agent
    |
    v
SigningTransport (wraps any MCP transport)
    |
    +---> Signs each tool call (Ed25519)
    +---> Appends Action Receipt to local audit log (hash-chained)
    +---> Forwards request to MCP server (unchanged)

Agent-side only. MCP servers don't need to change.

Action Receipt

Every tool call produces a signed receipt:

{
  "v": 1,
  "id": "rec_e7039e7e7714e84f...",
  "action": {
    "tool": "github_create_issue",
    "params": {"title": "fix bug"},
    "params_hash": "sha256:b878192252cb...",
    "target": "mcp://github.local",
    "transport": "stdio"
  },
  "signer": {
    "pubkey": "ed25519:0CRkURt/tc6r...",
    "name": "demo-bot",
    "owner": "willamhou"
  },
  "ts": "2026-03-29T23:24:03.309Z",
  "nonce": "rnd_dcd4e135799393...",
  "sig": "ed25519:6KUohbnSmehP..."
}

The signature covers the entire receipt body (action + signer + timestamp + nonce) using RFC 8785 (JCS) canonical JSON. Modifying any field invalidates the signature.

CLI Commands

Command	Description
`signet identity generate --name <n>`	Generate Ed25519 identity (encrypted by default)
`signet identity generate --unencrypted`	Generate without encryption (for CI)
`signet identity list`	List all identities
`signet identity export --name <n>`	Export public key as JSON
`signet sign --key <n> --tool <t> --params <json> --target <uri>`	Sign an action
`signet sign --hash-only`	Store only params hash (not raw params)
`signet sign --output <file>`	Write receipt to file instead of stdout
`signet sign --no-log`	Skip audit log append
`signet verify <receipt.json> --pubkey <name>`	Verify a receipt signature
`signet verify --chain`	Verify audit log hash chain integrity
`signet audit`	List recent actions
`signet audit --since <duration>`	Filter by time (e.g. 24h, 7d)
`signet audit --tool <substring>`	Filter by tool name
`signet audit --verify`	Verify all receipt signatures
`signet audit --export <file>`	Export records as JSON
`signet claude install`	Install Claude Code plugin (PostToolUse signing hook)
`signet claude uninstall`	Remove Claude Code plugin

Passphrase via interactive prompt or SIGNET_PASSPHRASE env var for CI.

Documentation

Doc	Description
Architecture	System design, component overview, data flow
Security	Crypto primitives, threat model, key storage
MCP Integration Guide	Step-by-step MCP setup with SigningTransport
CI/CD Integration	GitHub Actions example, key management for CI
Audit Log Guide	Querying, filtering, hash chain verification
Contributing	Build instructions, development workflow
Changelog	Version history

Project Structure

signet/
├── crates/signet-core/       Rust core: identity, sign, verify, audit, keystore
├── signet-cli/               CLI tool (signet binary)
├── bindings/
│   ├── signet-ts/            WASM binding (wasm-bindgen)
│   └── signet-py/            Python binding (PyO3 + maturin)
├── plugins/
│   ├── claude-code/          Claude Code plugin (WASM signing + audit)
│   └── codex/                Codex CLI plugin (WASM signing + audit)
├── packages/
│   ├── signet-core/          @signet-auth/core — TypeScript wrapper
│   ├── signet-mcp/           @signet-auth/mcp — MCP SigningTransport middleware
│   ├── signet-mcp-server/    @signet-auth/mcp-server — Server verification
│   ├── signet-mcp-tools/     @signet-auth/mcp-tools — Standalone MCP signing server
│   └── signet-vercel-ai/     @signet-auth/vercel-ai — Vercel AI SDK middleware
├── examples/
│   ├── wasm-roundtrip/       WASM validation tests
│   └── mcp-agent/            MCP agent, echo server, and verifier server example
├── docs/                     Design docs, specs, plans
├── LICENSE-APACHE
└── LICENSE-MIT

Building from Source

Prerequisites

Rust (1.70+)
wasm-pack
Node.js (18+)
Python (3.10+) + maturin (for Python binding)

Build

# Rust core + CLI
cargo build --release -p signet-cli

# WASM binding
wasm-pack build bindings/signet-ts --target nodejs --out-dir ../../packages/signet-core/wasm

# TypeScript packages
cd packages/signet-core && npm run build
cd packages/signet-mcp && npm run build
cd packages/signet-mcp-tools && npm run build

# Python binding
cd bindings/signet-py
pip install maturin
maturin develop

Test

# Rust tests (95 tests)
cargo test --workspace

# Python tests (160 tests)
cd bindings/signet-py && pytest tests/ -v

# WASM roundtrip (8 tests)
node examples/wasm-roundtrip/test.mjs

# TypeScript tests (26 tests)
cd packages/signet-core && npm test
cd packages/signet-mcp && npm test
cd packages/signet-mcp-server && npm test
cd packages/signet-mcp-tools && npm test

# Plugin tests (54 tests)
cd plugins/claude-code && npm test
cd plugins/codex && npm test

# Vercel AI SDK tests (5 tests)
cd packages/signet-vercel-ai && npm test

# Reference verifier server smoke test
cd examples/mcp-agent && npm run smoke

Security

Ed25519 signatures (128-bit security level, ed25519-dalek)
Argon2id key derivation (OWASP recommended minimum)
XChaCha20-Poly1305 key encryption with authenticated associated data (AAD)
SHA-256 hash chain for tamper-evident audit log
RFC 8785 (JCS) canonical JSON for deterministic signatures

Keys stored at ~/.signet/keys/ with 0600 permissions. Override with SIGNET_HOME env var.

What Signet proves

Agent key X signed intent to call tool Y with params Z at time T

What Signet does NOT prove (yet)

That the MCP server executed the action (use bilateral receipts with signResponse() for server co-signing — shipped in v0.4)
That signer.owner actually controls the key (planned: identity registry)

Signet is an attestation tool (proving what happened), not a prevention tool (blocking bad actions). It complements policy enforcement tools like firewalls and gateways.

License

Apache-2.0 + MIT dual license.

Signet MCP Tools

Quick Install