Verity Mcp

io.github.meloliva14Published by GitHub account meloliva14v0.3.0Updated Oct 24, 2026

Fail-closed verify-before-you-act gate for AI agents. Signed receipts. Pay-per-call via x402.

VerifiedSTDIODesktop onlyFinanceSecurity & MonitoringAI & ML

Overview

AI-generated overview

VerityLayer's local MCP server that gives an assistant paid, fail-closed trust checks: claim verification, prompt-injection screening, PII redaction and action-

What you can do
Verify claims at three tiers: a cheap quick check, a web-grounded check with citations, and a premium synthesis tier for high-stakes facts. Screen untrusted text and tool output for prompt-injection before acting on it. Moderate content as allow, review or block, and detect PII or secrets with a redacted version returned. Gate irreversible actions with an allow, review or block decision right before they run. Verify Ed25519-signed verdict receipts for free, without payment.
When to use it
Use it when an agent needs an independent second opinion before acting on a claim or running an irreversible action, or when untrusted text, content and personal data must be screened first. The free receipt check is useful for auditing verdicts already received.
Requirements
Runs locally over stdio as the PyPI package verity-mcp, started with uvx or pip; Node.js is not needed. Network access to the Verity engine and suite endpoints. Paid verdicts need the x402 extra and a funded Base-mainnet wallet in VERITY_WALLET_KEY; without it, paid tools return payment_required and no verdict. Optional variables set the engine and suite URLs, timeout and disclosed prices.
Before you install
Paid tools cost $0.02 to $0.35 per call in USDC on Base mainnet, and VERITY_WALLET_KEY can spend from that wallet, so use a dedicated low-balance wallet. Without a wallet, paid tools never return a verdict and the response warns not to treat it as allow. Claims, untrusted text and content submitted for checks are sent to VerityLayer's remote endpoints. The optional affiliate_id is forwarded as a referral tag.

Installation

In SourceWeft

  1. Open Verity Mcp in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

mcp-name: io.github.meloliva14/verity-mcp

Verity MCP — verify before you act

The official Model Context Protocol server for VerityLayer: independent, fail-closed trust checks any MCP-capable agent can discover and call. Fact-check a claim, screen for prompt-injection, catch PII, and gate irreversible actions — each check returns a calibrated verdict and abstains rather than guess. Payment is pay-per-call via x402 (USDC on Base mainnet). Verity holds no private key and never charges silently.

Name note: this is VerityLayer's official server — PyPI package verity-mcp, npm package @veritylayer/mcp. The npm package named verity-mcp is an unrelated third-party project.

Tools & pricing (every docstring states its price up front)

ToolPriceGrounded?What it's for
quick_verify$0.02no (Haiku)Cheap reality-check on a claim — the loopable default. Run everywhere, escalate the load-bearing ones.
grounded_verify$0.25yes (Sonnet, live web citations)The default product — web-grounded with cited evidence, for facts that matter before you act on them.
pro_verify$0.35yes (Opus, premium synthesis)The deepest tier — high-stakes claims where the grounded answer isn't confident enough to act on.
verify_receiptfree—Statelessly verify a signed Ed25519 verdict receipt — the audit trail / second opinion, no payment.
detect_injection$0.02—Screen untrusted text / tool output for prompt-injection before acting on it.
moderate_content$0.02—Is this safe to publish? (allow / review / block priced identically — no block-to-bill.)
redact_pii$0.02—Does this leak PII or secrets? Returns findings + a redacted version.
guard_action$0.02—The money-line gate: allow / review / block right before an irreversible action.

Quickstart

With uv (recommended — Claude Desktop / any MCP client):

json
{  "mcpServers": {    "verity": {      "command": "uvx",      "args": ["verity-mcp"]    }  }}

Or with pip:

bash
pip install verity-mcpverity-mcp        # stdio MCP server

That gets you the tools and the free verify_receipt. To get paid verdicts, read the next section — it's the part most people trip on.

How payment works

Verity's endpoints answer HTTP 402 (Payment Required) until the disclosed USDC micro-payment is settled. There are two ways to do that.

Wallet mode — get real verdicts (recommended)

json
{  "mcpServers": {    "verity": {      "command": "uvx",      "args": ["--from", "verity-mcp[x402]", "verity-mcp"],      "env": { "VERITY_WALLET_KEY": "0x…" }    }  }}

Point VERITY_WALLET_KEY at a funded Base-mainnet wallet and this server settles each call itself — the paid tools return real verdicts. Your key never leaves the process: it signs an EIP-3009 authorization locally for the exact amount each challenge discloses, and Verity only ever receives the signature. Nothing is charged silently; every price is disclosed up front.

Use a dedicated, low-balance wallet. This key can spend. Fund it with a few dollars of USDC on Base — calls cost $0.02–$0.35.

Keyless — the default

With no key set, this server holds nothing and pays nothing: a 402 is surfaced transparently (price restated, challenge attached) for an x402-capable caller to settle.

Be aware of the honest caveat: no shipping MCP client — Claude Desktop, Claude Code, Cursor, Windsurf — settles x402 today. So in keyless mode the paid tools will return payment_required and no verdict, forever. That's not a bug and it isn't hidden: the response says NO VERDICT WAS PRODUCED. Do not proceed as if this returned allow. If you want verdicts from an ordinary MCP client, use wallet mode.

verify_receipt is a free route, never 402s, and needs no wallet — you can check our signatures before you ever pay us.

Signed receipts — don't take Verity's word for it

Every paid verdict ships with an Ed25519-signed receipt: self-contained cryptographic proof of exactly what Verity said about exactly what claim, verifiable forever. Check any receipt free with the verify_receipt tool, offline against the public key at /.well-known/verity-pubkey.json, or live: curl https://api.veritylayer.dev/receipt/selftest.

Configuration (all optional)

Env varDefaultPurpose
VERITY_WALLET_KEY(unset — keyless)Optional. Private key of a funded Base wallet. Set it (with the [x402] extra) and this server settles its own payments, so paid tools return real verdicts. Never leaves the process; never logged.
VERITY_ENGINE_URLhttps://api.veritylayer.devFlagship claim-verification engine
VERITY_SUITE_URLhttps://suite.veritylayer.devTrust-check suite (injection/moderation/PII/guardrail)
VERITY_TIMEOUT90HTTP timeout (seconds)
VERITY_PRICE_QUICK$0.02Disclosed price echo for quick_verify
VERITY_PRICE_GROUNDED$0.25Disclosed price echo for grounded_verify
VERITY_PRICE_PRO$0.35Disclosed price echo for pro_verify
VERITY_PRICE_SUITE$0.02Disclosed price echo for the suite checks

Referral tag (reserved)

Every tool accepts an optional affiliate_id, forwarded as an X-Verity-Ref header. It never changes price, gating, or the verdict — it only tags who routed the call, and it is reserved for a future referral program: no split is paid today, and none will be until public terms are published at veritylayer.dev.

Links

Independent · fail-closed · keyless · pay-per-call. The only trust form an autonomous agent can pick up mid-task with no human and no account.

Source: README.md at commit 4524451

Tools

0
SourceWeft has not started this package in its sandbox yet, so its tools are not known.

Version history

1
  1. v0.3.0LatestSep 16, 2026

Score

40% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 days25 pts

    Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.

  • Auth declared10 pts

    Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.

  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts

    Declare a license in the repository or the registry entry.