Agent Evidence API MCP server
Commit Nov 5, 2026Provides cited, source-grounded web evidence, claim verification, and US weather alerts for AI agents via HTTP or MCP.
Also known as Thx93/agent-evidence-api, agent-evidence-api
- Stars
- 0
- Tools
- 8
- Downloads, 30 days
- —
- Latest version
- 0.1.9
- Last commit
- Nov 5, 2026
- License
- MIT
What is Agent Evidence API MCP?
Agent Evidence API provides cited, source-grounded web evidence, claim verification, and US weather alerts for AI agents via HTTP or MCP. It exposes 8 tools, such as research_evidence, health, initialize.
Summary generated from the project's README
About Agent Evidence API MCP server
Agent Evidence API provides AI agents with cited, source-grounded web evidence and US weather data. It functions through both HTTP endpoints and the Model Context Protocol, allowing developers to verify claims against specific URLs. The service returns excerpts, source URLs, retrieval timestamps, and content hashes, alongside an assessment of whether the evidence is supported, contradicted, mixed, or inconclusive.
Users access the service via HTTP POST requests or by running the MCP server through stdio using npx. There are no accounts or API keys required to use the tools. Instead, the service uses the x402 protocol for payments in USDC on the Base network. Each successful call costs $0.01, but no payment is taken if no sources can be retrieved. For weather data, the service pulls directly from the National Weather Service to provide alerts and forecasts for US locations.
This tool differs from standard search engines because it does not discover sources; it requires the user to provide the URLs. This ensures strict provenance for every piece of evidence provided to the agent.
What you can do with it
- 1Verify web claimsAn AI agent can check if a specific statement is supported by the content of a provided URL.
- 2Monitor US weatherA developer can request current weather alerts or forecasts for specific US states or coordinates.
- 3Audit source provenanceAn agent can trace information back to a specific retrieval to ensure the data has not been altered.
Written from the project's README. Every use case is checked against a quote from it.
How to install Agent Evidence API MCP
Formats verified 10 Nov 2026Add to CursorAdd to GooseInstall Agent Evidence API MCP in Claude Code
$ claude mcp add --transport http agent-evidence-api https://agent-evidence.thx93.dev/mcpInstall Agent Evidence API MCP in Cursor
~/.cursor/mcp.json
{
"mcpServers": {
"agent-evidence-api": {
"url": "https://agent-evidence.thx93.dev/mcp"
}
}
}Install Agent Evidence API MCP in VS Code
.vscode/mcp.json
{
"servers": {
"agent-evidence-api": {
"type": "http",
"url": "https://agent-evidence.thx93.dev/mcp"
}
}
}Install Agent Evidence API MCP in VS Code CLI
$ code --add-mcp '{"name":"agent-evidence-api","type":"http","url":"https://agent-evidence.thx93.dev/mcp"}'Install Agent Evidence API MCP in Codex
$ codex mcp add agent-evidence-api --url https://agent-evidence.thx93.dev/mcpInstall Agent Evidence API MCP in Codex config.toml
~/.codex/config.toml
[mcp_servers.agent-evidence-api] url = "https://agent-evidence.thx93.dev/mcp"
Install Agent Evidence API MCP in Gemini CLI
$ gemini mcp add -s user --transport http agent-evidence-api https://agent-evidence.thx93.dev/mcpInstall Agent Evidence API MCP in Gemini settings.json
~/.gemini/settings.json
{
"mcpServers": {
"agent-evidence-api": {
"url": "https://agent-evidence.thx93.dev/mcp",
"type": "http"
}
}
}Agent Evidence API MCP tools 8
Detected from the READMEresearch_evidencehealthinitializequestionurlsmax_sourceslanguagemode
| research_evidence | — | |
| health | — | |
| initialize | — | |
| question | — | |
| urls | — | |
| max_sources | — | |
| language | — | |
| mode | — |
Configuration
REASONING_PROVIDERX402_PRIVATE_KEY
| Name | Description | |
|---|---|---|
| REASONING_PROVIDER | — | |
| X402_PRIVATE_KEY | — |
Automated checks
Ran Nov 14, 2026Full report →Not verified yet. A server needs a score of 80, no serious finding, and enough data for us to check. How checks work · What to fix for more points
- Source repository linked and reachablethx93/agent-evidence-api is public and reachablegithub.com/thx93/agent-evidence-api ↗Pass
- Package names this repository as its sourceNot checked
- Build provenance (Sigstore attestation)Not checked
- Open source license (OSI)MITspdx.org/licenses/MIT.html ↗Pass
- Commit or release in the last yearLast commit or release 2026-11-05github.com/thx93/agent-evidence-api ↗Pass
- OpenSSF ScorecardNot checked
- Package name not close to a popular packageNot checked
- No critical advisory in the package or its dependenciesNot checked
- No hidden instructions to the model8 tool descriptions and the README read; no override phrases, credential paths or hidden charactersPass
- Destructive tools are labelledNo tool named like delete, drop or execPass
- Remote endpoint answers the MCP handshakeinitialize answered with protocol 2025-06-18 in 441 msPass
README
View on GitHubAgent Evidence API
Cited, source-grounded web evidence and claim verification, plus US weather from the National Weather Service, for AI agents — over both HTTP and MCP. Paid per call in USDC on Base over x402 — $0.01 a call, and nothing at all when nothing is retrieved. No API key and no account for either service.
| What | Where |
|---|---|
| HTTP evidence endpoint | POST https://agent-evidence.thx93.dev/v1/evidence |
| HTTP weather alerts | POST https://agent-evidence.thx93.dev/v1/weather/alerts — {"state":"TX"} |
| HTTP weather forecast | POST https://agent-evidence.thx93.dev/v1/weather/forecast — {"latitude":37.7749,"longitude":-122.4194} |
MCP service (research_evidence) |
POST https://agent-evidence.thx93.dev/mcp |
| MCP service over stdio (desktop clients) | npx -y @thx93/agent-evidence-mcp — pays x402 from your own wallet |
MCP service (get-alerts, get-forecast) |
POST https://agent-evidence.thx93.dev/weather/mcp |
| Free sample of real output | GET https://agent-evidence.thx93.dev/demo — an unedited response from an actual paid call, no wallet needed |
| Zero-install buyer CLI | curl -fsSL https://agent-evidence.thx93.dev/buy.mjs -o buy.mjs |
| x402 capability manifest (all five paid resources) | https://agent-evidence.thx93.dev/.well-known/x402 |
Discovery is free on every MCP route (tools/list, initialize, ping, and a
health tool), so an agent can read the schemas and probe for liveness before
paying for anything.
Optional: semantic ranking
Ranking is deterministic lexical matching by default, and it has a measured ceiling. Asked "What is the population of Tokyo?" it returns passages that mention "population" and "Tokyo" — 1603 history, wartime declines, municipal taxes — and misses the sentence that answers the question, because that sentence says "the city proper" instead of repeating "Tokyo". Two lexical heuristics were tried and reverted; no keyword trick bridges it.
An optional Laya sidecar closes it. Laya
is an open-weight (Apache-2.0) typed-decision model: it scores a passage with
noul, P(this passage directly answers the question). No vendor, no API key, no
per-call fee, and your content never leaves the host.
python services/laya/server.py # ~2 GB resident, ~35 s cold load
REASONING_PROVIDER=laya REASONING_URL=http://127.0.0.1:8077 ...
Measured on the case above, single source:
| Sources | none |
laya |
Top 3 contains the answer? |
|---|---|---|---|
| 1 | ~1.4 s | ~11.4 s | ❌ → ✅ |
| 5 | ~1.6 s | ~1.8 s (falls back) | ❌ → ❌ |
The model is engaged only when the budget can afford the full pool. Cost is
~800 ms per candidate (a single call measures ~420 ms, but the sidecar
serialises, so ~700 ms under real concurrency). The budget is divided across
sources, so 1–2 sources can afford a 12-wide pool and larger requests cannot. A
narrower pool was measured to be worthless — it can only reshuffle passages that
already excluded the answer — so rather than spend ~20 s on that, those requests
fall back to lexical and stay fast. Lower REASONING_POOL_SIZE to engage on
larger requests, trading recall.
The budget is a hard ceiling, not a target: it is reserved before each call, so concurrent sources cannot collectively overshoot it. (An earlier version checked and then awaited, which let five sources each pass the check before any decremented it — an 8 s budget produced a 50 s request.)
The trade is latency, not accuracy: ~420 ms per candidate, so a 12-candidate pool costs ~5 s of inference per source. That is why it is off by default. Enabling it changes only the ORDER of evidence — every excerpt, source, URL and hash is identical — and if the sidecar is missing, slow, or returns anything unexpected the service silently keeps its lexical result. The raw model probability is never exposed (SPEC §21).
Note the pool matters: the first version of this ranked only the 5 candidates lexical had already chosen, and the answer had been ranked 8th–20th, so it was never available to promote. The wider pool is what makes it work.
Running the backend in Docker? The sidecar must be reachable from the container:
--add-host=host.docker.internal:host-gateway and point REASONING_URL at
http://host.docker.internal:8077, or put both on one Docker network.
You are only charged when the service delivers
The x402 middleware settles a payment only when the handler returns a status below 400, so the service is built so that every way it can fail is a 4xx or 5xx:
- If no source could be retrieved — all 404s, all SSRF-blocked, all unsupported
content types — the request fails with
NO_SOURCES_RETRIEVED(502) and no payment is taken. An earlier version returned200 inconclusivehere, which would have billed a buyer $0.03 for an empty result. - Partial success still settles. If one of five sources was retrieved, real evidence was delivered and the per-source warnings explain the rest.
- On the MCP transport, a failed tool call is reported as
isError: trueinside an HTTP 200 — correct MCP behaviour, but invisible to the payment middleware. The Worker rewrites that to 502 so the payment is not taken; the JSON-RPC body is passed through unchanged.
Verified against the live deployment: a request whose sources all fail returns
502 NO_SOURCES_RETRIEVED, and a request with one good source plus one dead one
returns 200.
Try it without paying
Every paid route has a free preview that returns a real, unedited result — not a mock:
curl -s -X POST https://agent-evidence.thx93.dev/v1/evidence/preview \
-H 'content-type: application/json' \
-d '{"question":"What is a centrifugal pump used for?",
"url":"https://en.wikipedia.org/wiki/Centrifugal_pump"}'
curl -s 'https://agent-evidence.thx93.dev/v1/weather/alerts/preview?state=TX'
curl -s 'https://agent-evidence.thx93.dev/v1/weather/forecast/preview?latitude=37.7749&longitude=-122.4194'
The evidence preview returns one source and up to three excerpts with source URL, retrieval time and content hash, but no assessment. The paid call takes up to five sources and adds the supported / contradicted / mixed / inconclusive verdict.
Twenty-five previews per caller address per day, no account, no wallet. The paid routes are deliberately separate: they must keep answering 402, because that is what every x402 catalogue and validator checks, so previewing them in place would make the service unlistable.
FAQ
What is Agent Evidence API?
An HTTP and MCP service for AI agents that returns cited, source-grounded evidence from
public web pages, plus US weather from the National Weather Service. You send a question
and up to five URLs; it returns the passages that bear on the question with their source
URL, retrieval time and content hash, and an assessment of supported, contradicted,
mixed or inconclusive.
Do I need an API key or an account? No. There is nothing to sign up for. Payment is per call in USDC on Base over x402, so an agent with a wallet can pay for exactly what it uses.
How much does it cost? 0.01 USDC per call. Nothing is charged when nothing is retrieved — if a source cannot be fetched or no evidence is delivered, settlement is cancelled.
Can I see the output before paying?
Yes. GET /demo (HTML) and GET /demo.json serve one complete, unedited evidence
package from a real paid call. The MCP sample tool returns the same thing, free.
How is this different from a search engine or a scraper? It is neither. You supply the URLs; the service does not discover sources for you. What it adds is provenance: every excerpt is tied to a real retrieval, with a timestamp and a content hash, so a claim can be traced back to what the page actually said.
What are its limits?
Matching is deterministic and lexical, not semantic. When a question asks more than one
thing and only one source contributed a matching passage, the service answers
inconclusive rather than guessing. Weather is US only, because the data is the US
National Weather Service's.
How do I call it from an agent?
Over HTTP (POST /v1/evidence) or MCP (POST /mcp). The buyer CLI is zero-install:
curl -fsSL https://agent-evidence.thx93.dev/buy.mjs -o buy.mjs, or
npx @thx93/x402-evidence.
Market analysis
docs/market-analysis.md — what the x402 economy actually pays for, measured from the only catalogue that publishes real usage data (30-day calls and unique payers per service). It is uncomfortable reading: the category this service sits in is 1% of search by volume, and its price band is the weakest of the five.
Engineering report
docs/ENGINEERING-REPORT.md — the report required
by SPEC.md §44: what was built, the architecture, deployment and test commands,
x402 and MCP status, registry readiness, remaining manual configuration, and known
limitations. It states plainly what is demonstrated and what is not — including
that no settlement has been exercised and that one §42 acceptance criterion is
unmet. It does not claim the project is production ready.
Actions only you can take
docs/CHECKLIST.md — every remaining step that needs a human: the first payment, confirming the catalogue listing, posting, and the decisions I deliberately left to you. Everything else is done.
Making the first sale
See docs/FIRST-SALE.md — the whole path from an empty wallet to a settled payment and a catalogue entry, in one page.
How to see revenue
Every request the backend serves on a paid route has already passed the backend's own x402 payment gate (the Worker only proxies). The log is append-only on the data volume, so it survives container recreation and redeploys — unlike Docker logs.
A line means a payment proof was verified in this process. It is not proof of
settlement. The x402 order is verify → handler → settle, so the backend writes its
line before the facilitator settles, and a settlement that later fails still appears
here. The field is named payment_provided for that reason; it was previously
called settled, which was wrong.
docker exec aee-live cat /app/data/usage.jsonl # the raw record
# Buyer traffic: requests that carried an x402 payment proof, so operator and
# test calls are excluded. This is NOT a revenue figure - see below.
docker exec aee-live sh -c "grep -c '"payment_provided":true' /app/data/usage.jsonl"
For money, use the on-chain record. The buyer's client prints the settlement transaction, and the authoritative ledger is the recipient address:
https://basescan.org/address/0x9c0e2B44180439294Fa30Ae2B2a94f8655455FD0
Each line carries the timestamp, request id, a salted hash of the question (never the text), how many sources were retrieved, how many evidence items came back, the assessment, and the server-side duration.
{"ts":"2026-09-21T07:53:04.341Z","request_id":"req_2fcc…","question_hash":"725f50fca9fbe049",
"question_chars":32,"sources_requested":1,"sources_retrieved":1,"evidence_items":5,
"assessment":"supported","processing_ms":6,"outcome":"ok"}
For the on-chain side, the payment response carries a settlement transaction
hash, and the recipient is 0x9c0e2B44180439294Fa30Ae2B2a94f8655455FD0 — check it
on basescan.
Live deployment
| Endpoint | https://agent-evidence.thx93.dev |
| MCP | https://agent-evidence.thx93.dev/mcp |
| Health | /health · deep: /health?deep=1 |
| Registry | io.github.Thx93/agent-evidence-api — published, status active |
| Payment | x402, exact, 0.03 USDC on Base mainnet (eip155:8453) |
| Buy it | zero install: curl -fsSL .../buy.mjs -o buy.mjs && node buy.mjs "question" https://source.example |
Buy something with no npm account and nothing to install — the buyer CLI is a single self-contained file served by the service itself:
curl -fsSL https://agent-evidence.thx93.dev/buy.mjs -o buy.mjs
X402_PRIVATE_KEY=0x... node buy.mjs "Is Rotamech a manufacturer of centrifugal pumps?" https://example.com
Or just look at the paywall first — this returns a 402 and charges nothing:
curl -X POST https://agent-evidence.thx93.dev/v1/evidence \
-H 'content-type: application/json' \
-d '{"question":"Is Rotamech a manufacturer of centrifugal pumps?","urls":["https://example.com"]}'
Evidence infrastructure for AI agents. Give it a question or a claim plus the
public web pages you want checked, and it returns structured, cited evidence:
source URLs, retrieval timestamps, short evidence excerpts, metadata, and an
explicit supported / contradicted / mixed / inconclusive assessment.
It is reachable by agents over both HTTP and MCP, and it is paid per request with x402 + USDC on Base. There are no accounts, no passwords, and no API keys — the payment is the authentication.
- Product specification:
SPEC.md— the authority on requirements. - Engineering rules:
AGENTS.md— the sole project rule book. - Architecture:
docs/architecture.md
It provides evidence, not truth. The assessment is produced by deterministic lexical matching, and the service says
inconclusiverather than guessing. Do not treat asupportedstatus as proof.
Implementation status — read this first. Every package and both apps are implemented, and
pnpm typecheckpasses across the whole workspace.pnpm testcovers ~147 cases in six suites, including a cross-package end-to-end flow test.What is not done: no on-chain x402 payment has been demonstrated, there is no automated x402 payment test,
ROBOTS_POLICYis configured but inert, and two committed literal test wallet addresses inapps/worker/wrangler.jsoncneed replacing before any deployment. See Implementation status.
1. What the service does
An agent submits:
- a question or claim, and
- one or more public URLs to use as sources.
The service then:
- validates the URL and rejects anything unsafe (SSRF defences),
- fetches the page with bounded timeouts, redirects, and response size,
- detects the content type and parses the HTML,
- extracts metadata (title, description, canonical URL, Open Graph, JSON-LD, language, publication and modification dates, headings, word count),
- normalises the main content and produces a SHA-256 content hash,
- extracts short evidence excerpts that match the question, with their position in the document,
- compares the sources and reaches an assessment,
- returns a structured response with full provenance.
It is not a web scraper, an SEO tool, a generic crawler, a proxy, a browser-automation service, or a search engine. It is evidence infrastructure: the thing an agent calls when it needs to show its work.
What comes back
{
"request_id": "req_3f9c1a7b2e4d4a6f8b0c1d2e",
"version": "1",
"question": "Is Rotamech Industries a manufacturer of centrifugal pumps?",
"assessment": {
"status": "supported",
"basis": "1 source(s) contained passages matching the question (example.invalid) with no contradicting passages found."
},
"sources": [
{
"requested_url": "https://example.invalid/products",
"final_url": "https://example.invalid/products",
"status": 200,
"content_type": "text/html; charset=utf-8",
"title": "Rotamech Industries — Products",
"canonical_url": "https://example.invalid/products",
"description": "Rotamech Industries manufactures centrifugal pumps for industrial use.",
"publisher": "Rotamech Industries",
"language": "en",
"published_at": "2024-03-01T09:00:00.000Z",
"modified_at": null,
"retrieved_at": "2026-09-20T21:16:07.412Z",
"word_count": 63,
"content_hash_sha256": "3a7bd3e2360a3d29eea436fcfb7e44c735d117c42d1c1835420b6b9942dd4f1b",
"evidence": [
{
"excerpt": "Rotamech Industries is a manufacturer of centrifugal pumps.",
"context": "h2:Products > p[1]",
"relevance": "direct"
}
],
"structured_data": { "json_ld": [], "open_graph": {} },
"warnings": [],
"from_cache": false,
"redirect_chain": []
}
],
"limitations": [
"Assessment is derived from deterministic lexical matching, not semantic reasoning. A configured reasoning provider may refine it, but never replaces source evidence."
],
"processing_ms": 412
}
Every field is documented in docs/api.md.
2. Why an agent would use it
Because an agent that cites sources is more useful than one that asserts them.
- Grounding. Instead of generating a plausible sentence, the agent can attach a real URL, a retrieval timestamp, a content hash, and the passage the claim rests on.
- Verification. An agent can check what a specific page actually says, rather than trusting a summary.
- Comparison. Multiple sources are compared, and disagreement is reported as
mixedinstead of being averaged away. - Honesty by construction. When nothing matches closely enough, the answer is
inconclusive. The service never invents a fact, never pretends a source says something it does not, and never emits a confidence score. - No onboarding. No signup, no key, no plan. Discover the tool, call it, pay per request, get evidence.
3. Example use case
An agent has been asked: "Is Rotamech Industries actually a manufacturer of centrifugal pumps, or just a reseller?"
Its own model knowledge is stale and unverifiable, so it gathers candidate URLs, then calls this service:
{
"question": "Is Rotamech Industries a manufacturer of centrifugal pumps?",
"urls": [
"https://example.invalid/products",
"https://example.invalid/about",
"https://example.invalid/registry-record"
],
"max_sources": 5,
"language": "auto",
"mode": "evidence"
}
The company site supports the claim; the registry page negates it. The service returns:
{
"assessment": {
"status": "mixed",
"basis": "Sources disagreed: 2 leaning to support (example.invalid) and 1 leaning against (example.invalid)."
}
}
with short cited excerpts from each side, their retrieval timestamps, and their content hashes.
The agent now has something it did not have before: a defensible answer that names both sides and shows where each came from, plus honest limitations. It can tell the human "the company claims this; a registry record disputes it; here are both sources", instead of picking one and sounding confident.
4. MCP usage
Transport: streamable HTTP. Endpoint: /mcp on the same host as the API.
${MCP_PUBLIC_URL} e.g. https://${PUBLIC_API_DOMAIN}/mcp
Tools
| Tool | Payment | Purpose |
|---|---|---|
research_evidence |
paid (x402) | Fetch public sources and return structured, cited evidence. |
health |
free | Status check. |
Example client configuration
{
"mcpServers": {
"agent-evidence-api": {
"type": "http",
"url": "${MCP_PUBLIC_URL}",
"headers": {
"Accept": "application/json, text/event-stream"
}
}
}
}
There is nothing to put in headers for authentication. There is no key.
initialize and tools/list are free
This matters for autonomous agents, and it is deliberate:
| JSON-RPC method | Paid? |
|---|---|
initialize |
free |
tools/list |
free |
tools/call → health |
free |
tools/call → research_evidence |
paid |
| everything else | free |
An agent must be able to discover the tools before it can decide to pay for one. Only an actual invocation of the paid tool requires payment. A JSON-RPC batch is charged if any element is a paid call.
Example tool call
{
"jsonrpc": "2.0",
"id": 2,
"method": "tools/call",
"params": {
"name": "research_evidence",
"arguments": {
"question": "Is Rotamech Industries a manufacturer of centrifugal pumps?",
"urls": ["https://example.invalid/products"],
"max_sources": 5,
"language": "auto",
"mode": "evidence"
}
}
}
Tool input schema (identical to the HTTP request body):
| Field | Type | Required | Notes |
|---|---|---|---|
question |
string |
yes | 1–2000 characters. |
urls |
string[] |
no | At most 25 in the schema, 5 by default at runtime. |
max_sources |
integer |
no | Positive, ≤ 25. |
language |
string |
no | "auto" or a BCP-47 tag. |
mode |
"evidence" |
no | The only value in v0.1.0. |
Full details, including what a payment-required response looks like to an MCP
client: docs/mcp.md.
5. HTTP usage
GET /health free liveness
GET / free capabilities
POST /v1/evidence paid the evidence resource
GET /health
curl -s https://${PUBLIC_API_DOMAIN}/health
{ "status": "ok", "service": "agent-evidence-api", "version": "0.1.6" }
GET /
A free capability description, useful for discovery before paying.
curl -s https://${PUBLIC_API_DOMAIN}/
{
"service": "agent-evidence-api",
"version": "0.1.6",
"description": "Evidence infrastructure for AI agents. Returns structured, cited, freshly-retrieved evidence from public web pages so an agent can verify claims and ground answers in sources.",
"endpoints": {
"health": "GET /health (free)",
"evidence": "POST /v1/evidence (paid, x402)",
"mcp": "POST /mcp (MCP streamable HTTP; initialize and tools/list are free)"
},
"mcp": { "transport": "streamable-http", "tools": { "research_evidence": "paid", "health": "free" } },
"payment": {
"protocol": "x402",
"scheme": "exact",
"network": "eip155:84532",
"asset": "USDC",
"price_usd": "0.03",
"recipient": "0x…",
"facilitator": "https://x402.org/facilitator"
}
}
POST /v1/evidence
POST /v1/evidence HTTP/1.1
Host: ${PUBLIC_API_DOMAIN}
Content-Type: application/json
payment-signature: <x402 payment proof>
{
"question": "Is Rotamech Industries a manufacturer of centrifugal pumps?",
"urls": ["https://example.invalid/products", "https://example.invalid/about"],
"max_sources": 5,
"language": "auto",
"mode": "evidence"
}
Returns the EvidenceResponse document shown in §1.
Without valid payment you get HTTP 402 with a PAYMENT_REQUIRED error envelope
and the x402 payment requirements:
{
"error": {
"code": "PAYMENT_REQUIRED",
"message": "Payment is required to access this resource.",
"request_id": "req_5c4b3a291807f6e5d4c3b2a1"
}
}
Agent Evidence API MCP questions
How do I add Agent Evidence API MCP to Claude Code?
Run claude mcp add --transport http agent-evidence-api https://agent-evidence.thx93.dev/mcp in your terminal. Add --scope user to make it available in every project.
How do I add Agent Evidence API MCP to Cursor?
Open ~/.cursor/mcp.json and add the server under mcpServers, using the Cursor config shown in the install section above.
What tools does Agent Evidence API MCP provide?
It exposes 8 tools, including research_evidence, health, initialize, question, urls.
What is Agent Evidence API?
It is an HTTP and MCP service for AI agents that returns cited, source-grounded evidence from public web pages, plus US weather from the National Weather Service.
Do I need an API key or an account?
No, there is no sign-up required. Payment is handled per call using USDC on Base via x402, allowing agents with a wallet to pay for usage.
How much does it cost?
The service costs 0.01 USDC per call, but you are not charged if no evidence is retrieved or if a source cannot be fetched.
Can I see the output before paying?
Yes, you can use the free preview routes or the demo endpoints to see real, unedited evidence packages without needing a wallet.
How is this different from a search engine or a scraper?
Unlike search engines, it does not discover sources; you must provide the URLs. Unlike scrapers, it provides provenance by tying every excerpt to a specific retrieval, timestamp, and content hash.