agentverify-checks
AgentVerify (early pilot)
Try it now: a free, AI-run live demo with a shared public key is described in DEMO.md (https://agentverify-checks.onrender.com), and the remote MCP endpoint is https://agentverify-checks.onrender.com/mcp.
AgentVerify is an early, free service that performs deterministic calculation checks and returns signed Ed25519 receipts for the results. It can be used as a local stdio MCP server or, opt-in, as a remote MCP endpoint alongside a small FastAPI HTTP API.
Status: early software, free, no SLA and no support commitment. The supported way to use it is to install and run it yourself. The operator also runs a free AI-run demo instance (see DEMO.md) that sleeps when idle, may be offline or slow, and needs an API key; its remote MCP endpoint is switched on and has been tested on loopback and with an outside connection, not under load. It is not production qualified, makes no high-availability claims, has had no security certification or audit, and makes no payment-revenue claims.
Quickstart
From a clean clone (tested only on Python 3.14 on Windows; other versions and platforms are untested):
python -m venv .venv
# Windows: .venv\Scripts\activate Linux/macOS: source .venv/bin/activate
pip install -r requirements.txt
python -B pilot_v340.pyThe pilot script starts a local server on 127.0.0.1 with throw-away keys, runs its own checks and prints a pilot_status; PASS is the expected result. Tests: python -B tests_av013.py, python -B tests_x402.py, python -B tests_claimsource.py.
Related MCP server: ArtifactGuard
Verifying a receipt
Signed receipts (/verify/signed) contain payload, algorithm (Ed25519), public_key and signature. Check one offline with the bundled client, using an issuer public key you obtained from a source you trust (not the key inside the receipt):
from agentverify_client import verify_receipt
ok = verify_receipt(receipt, trusted_public_key) # True only if signed by that key and unmodifiedIssuerTrustStore in the same package lets you pin several issuer keys and mark them active, retired or revoked. A valid signature proves integrity and issuer identity only, not that a claim is true.
A sample receipt is in examples/sample_receipt.json: rule_version agentverify-0.8.0, produced by the current code through the remote MCP tool verify_and_sign on 2026-11-20 with a throw-away signing key (discarded; the embedded public key belongs to no real issuer). It only shows the format; tests_av013.py checks that it still verifies against its own embedded key, which proves nothing about any real issuer.
MCP
Local stdio (the default):
python -m app.mcp_server. Tools:verify_calculation,verify_batch,verify_and_sign,check_signed_receipt,get_public_key.Remote (opt-in, off by default): set
AGENTVERIFY_REMOTE_MCP=1together withAGENTVERIFY_PUBLIC_MODE=1; the endpoint is/mcp(Streamable HTTP, stateless) and needs the sameX-API-Keyheader as the HTTP API. Hosts other than loopback must be listed inAGENTVERIFY_MCP_ALLOWED_HOSTS(exact host names, no wildcards); otherHostandOriginvalues are rejected. It was verified locally on loopback only (AV-027): tool listing, a signed arithmetic check and a signed claim-vs-source check over the MCP client library, receipts verified withagentverify_client, and a wrongHost, a badOriginand a missing or wrong key were all rejected. The free demo has it switched on (host agentverify-checks.onrender.com); from outside, initialize and tools/list were checked with the demo key. It has not been tested under load.
Claim-vs-source checks (AV-018)
Besides arithmetic, three deterministic categories check whether text you supply contains what an agent claims it says. Use them on the same routes (/verify, /verify/batch, /verify/signed) and the same MCP tools; they can be mixed with arithmetic items in one batch. No network access: the service never fetches anything (see DESIGN_URL_MODE.md for why, and how a fetcher might be added safely).
| Claim field | Other fields | Passes when |
|
|
| the normalised quote is an exact substring of the normalised source |
|
|
| a standalone number in the source equals the claim within tolerance |
|
|
| the same calendar date appears in ISO, |
{"calculation_type":"number_in_text","claimed_result":"3200000","unit":"$","allow_scaling":true,"source_text":"Seed funding was $3.2m in 2025."}
-> {"status":"passed", ... "evidence":{"source_sha256":"e38ffc65...","found":true,"match_offset":18, ...}}Normalisation (
av-text-norm-1): Unicode NFC; curly quotes mapped to'/"; all dashes and the minus sign mapped to-;…to...; soft hyphen, zero-width space, word joiner and BOM removed; every run of Unicode whitespace collapsed to one space and trimmed; optional casefold for quotes only. Nothing else (no stemming, no NFKC, no synonyms).Numbers are exact
Decimals, never floats.12.50equals12.5(numeric equality).1234never matches inside12345or21234. Thousands separators (1,234.5) are understood;1,23and1.2.3are not numbers. A number directly followed byk/m/bn/b(or followed by a space andthousand/million/billion/bn/mn) is a scaled number: it matches only withallow_scaling: true(then3.2mis 3200000, and no longer matches 3.2). A suppliedunit($ £ € ¥ %or up to 8 letters) must sit next to the number; withoutunit, the unit is not checked.Dates: ambiguous numeric forms like
01/02/2026are never matched unless you statedate_format. Impossible dates in the text (31 February 2026) never match.Receipts (
/verify/signed) bind the claim and the source: the signed payload holds the claim, the options, the normalisation version/flags and the SHA-256 of the normalised source text, and never the source text itself. Anyone holding the same text can normalise it with the published rules, hash it, and compare. Changing the claim or the hash breaks the signature. Theagentverify_clientverifier (see above) works on these receipts.Limits:
source_text1-65536 characters (and the whole request stays under the 64 KiB body cap); one invalid item rejects a whole batch with 422, as before.
What this does and does not prove. A pass means the supplied text contains the claim after normalisation. It does not prove the claim is true, that the text is the real or current source, or that it was not edited before you sent it. There is no semantic matching: a paraphrase fails. Tests: python -B tests_claimsource.py.
Honest limits
Early software. Free. No SLA and no support commitment.
Single worker only; the rate limit is in-process and is not shared between processes or hosts.
The HTTP 402 response (
/payments/preview, opt-in) is an illustrative preview only. No payments exist and nothing is charged or processed.No production hosting claims are made. Do not treat this as a hardened, hosted service.
Receipts are only as trustworthy as the signing key you configure. Protect that key; anyone holding it can issue valid receipts.
Known limits
F03, magnitude rule (Medium): inputs and claims must have a magnitude between roughly 1E-18 and 1E+18 (at most 30 digits). Some correct but very large or very small results (e.g. 1E+17 x 1E+17) are rejected with HTTP 422. These are false rejections, not wrong answers. Not changed.
F04, idempotency key can stay stuck (Medium, suspected): read from the code, not executed (needs PostgreSQL). After a quota or transient failure an
Idempotency-Keymay stay blocked until retention ends; use a new key.F05, durable credentials are Windows-only (Medium): the durable credential store (and therefore idempotency) works only on Windows and fails closed elsewhere. The default static-key mode is unaffected.
Single worker only; the rate limit and the replay store are in-process. PostgreSQL paths and cloud recovery were not verified; remote MCP was verified on loopback only (see MCP above). Tested on one Windows machine only.
Never run a reverse proxy in front of the local-dev bypass, and never enable that bypass on a shared host.
x402 (experimental, testnet-only)
Optional pay-per-call support under the x402 standard, so a caller without an API key can pay a small per-call price instead. It is OFF by default: unless AGENTVERIFY_X402_ENABLED=1, nothing changes and the x402 package is not even imported. API keys keep working and bypass payment.
It has been built and tested against a fake in-process facilitator only. No payment has ever been tested with real funds, and no wallet key is involved or needed (the service only holds a public receiving address).
x402 payment volumes are small today; this is an option for the owner, not a revenue claim.
Mainnet is refused unless two extra flags are set. Taking real payments needs owner decisions that have not been made (receiving address, production facilitator, price, hosting).
Details, configuration and the owner checklist: X402.md. Tests: python -B tests_x402.py.
License
MIT, see LICENSE.
Agent skill
skill/SKILL.md is a ready-made agent skill that tells an AI agent when and how to call the demo (or a self-run copy) and how to describe what a receipt does and does not prove. Copy it into your agent's skills folder if you want to use it. It is a plain file in this repository, not a listing on any marketplace.
Available Tools
5 toolscheck_signed_receiptB
Check whether an AgentVerify receipt has an intact signature from this local issuer.
Inputs: receipt (required). Returns: object
get_public_keyB
Return the public signing key for this AgentVerify instance.
Inputs: no named parameters. Returns: object
verify_and_signB
Check a numerical claim and issue a locally signed Ed25519 receipt. The signature proves integrity and local issuer identity, not the truth of supplied inputs.
Inputs: request (required). Returns: object
verify_batchA
Check up to 50 numerical claims in one call. Each item has calculation_type, claimed_result, inputs and optional tolerance.
Inputs: requests (required). Returns: object
verify_calculationB
Check a claimed numerical result. Request fields: calculation_type, claimed_result, inputs, optional tolerance. Returns passed/failed and independently calculated result. Claim-vs-source categories (quote_in_text, number_in_text, date_in_text) take source_text you supply plus claim_text (or claimed_result for numbers); they prove only that the supplied text contains the claim, not that it is true.
Inputs: request (required). Returns: object
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 5 tools
Each tool targets a distinct operation: single verification, batch verification, verification with signing, receipt signature check, and public key retrieval. The only mild overlap is between verify_calculation and verify_and_sign, but the descriptions make the signing distinction explicit.
All names are snake_case and verb-led (verify_*, check_*, get_*), forming a predictable pattern throughout. verify_and_sign is slightly longer but still follows the convention.
Five tools is well-scoped for a verification-and-signing service, with each tool earning its place. No redundant or filler tools are present.
The surface covers the core lifecycle: verify, batch verify, sign, check receipt, and retrieve public key. Minor gaps exist, such as no batch signing or receipt listing/retrieval, but core workflows are covered.
Maintenance
Related MCP Connectors
One-stop claim verification for AI agents: verdicts with confidence, evidence, signed receipts.
Deterministic signed verification of numeric & financial claims for AI agents & spreadsheets.
Deterministic fact verification for AI agents — checksums & curated data, not guesses.
Independent signed math checks for AI agents: PASS or FAIL plus a link anyone can open. Free beta.
Related MCP Servers
AlicenseAqualityCmaintenanceThe deterministic fact-verification layer for AI agents. Validates the structured facts an agent emits — IBANs, payment cards, VAT and national tax IDs, crypto and bank addresses, domains, emails, phone numbers, securities and academic identifiers, plus dates, currencies and holidays — against checksums and curated authoritative data, not guesses.561Apache 2.0- FlicenseNot gradedqualityBmaintenanceEnables AI agents to validate deliverables (JSON, ZIP, PDF, DOCX) against signed contracts, generating verifiable receipts with Ed25519 signatures.-
- AlicenseAqualityBmaintenanceAppend-only evidence receipts for AI records: seal, verify, cite, chain-check, anchor status. A seal proves a record existed at a time, not that its contents are true. Five tools over stdio with npx -y apex-psi-mcp — no account, no key, verification free forever.5826 npm1MIT
- AlicenseNot gradedqualityDmaintenanceEnables AI agents to verify claims deterministically by computing arithmetic, ratios, and dates and matching statements against provided sources, returning a confidence ladder of certain, source-backed, or unverifiable.MIT