# Fact Verification MCP (remote · fact-check-mcp-production.up.railway.app)

Verify claims with verdict, confidence & cited sources; batch verify, source checks, daily brief.

- Trust score: 50/100 (low)
- Change this week: −11
- Registry status: active
- Liveness: degraded
- Owner verified: no
- Last scored: 2026-08-04

> **Degraded**: one or more channels of this server are currently unreachable; their trust score is decaying and will reach 0 if they stay down.

## Components

- remote · `fact-check-mcp-production.up.railway.app`: 50/100 (this document), [markdown](https://verifymcp.io/servers/foundrynet-fact-check-mcp/fact-check-mcp-production.md), [page](https://verifymcp.io/servers/foundrynet-fact-check-mcp/fact-check-mcp-production)

## Channel facts

- Endpoint: `https://fact-check-mcp-production.up.railway.app/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `1.0.0`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-08-04.

- **Endpoint Security**: 57/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation not yet verified: we couldn't confirm whether this endpoint requires it.
  - HTTPS is enforced; there's no plaintext access path.
  - HSTS not yet verified: we couldn't read the response headers to check for it.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 0/100
  - Transport check failed: declared streamable-http, but we couldn't connect to verify it.
- **Schema Quality & AI Usability**: 0/100
  - Schema not yet verified: we couldn't read the endpoint's schema.
- **Stability & Change Management**: 0/100
  - Stability not yet verified: not enough scan history yet (needs a 30-day window).
- **Tool Coverage**: 0/100
  - Tool coverage not yet verified: we couldn't read the endpoint's tools.
- **Capabilities**: 0/100
  - Capabilities not yet verified: we couldn't read the endpoint's capabilities.

**Unverified: 4 categories.** Categories scored 0 because we could not verify them: authentication we do not have, an unreachable endpoint, or not enough scan history. We only credit what we can confirm.

## Install

### Claude

```bash
claude mcp add --transport http foundrynet-fact-check-mcp https://fact-check-mcp-production.up.railway.app/mcp
```

### Codex

```toml
[mcp_servers.foundrynet-fact-check-mcp]
url = "https://fact-check-mcp-production.up.railway.app/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "foundrynet-fact-check-mcp": {
      "type": "remote",
      "url": "https://fact-check-mcp-production.up.railway.app/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add foundrynet-fact-check-mcp --url https://fact-check-mcp-production.up.railway.app/mcp --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  foundrynet-fact-check-mcp:
    url: "https://fact-check-mcp-production.up.railway.app/mcp"
```

### Other

```json
{
  "mcpServers": {
    "foundrynet-fact-check-mcp": {
      "type": "http",
      "url": "https://fact-check-mcp-production.up.railway.app/mcp"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-08-02 (score 50, −12)

The score moved with no change recorded against any check. We would rather say so than guess.

### 2026-07-31 (score 62, 0)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-30 (score 62, 0)

- [security regression] Endpoint reachability: reachable → unreachable
- [security regression] Stability: 0.10 → unverified
- [security regression] HSTS header: fail → unverified
- [security regression] Transport: pass → fail
- [security] Authorization: Authorisation not yet verified: we couldn't confirm whether this endpoint requires it.
- [functional regression] Capabilities: pass → unverified
- [functional regression] Tool coverage: 100 → unverified
- [functional] First check of Schema quality: unverified

### 2026-07-29 (score 62, +1)

No change was recorded against any check on this day. Stability & Change Management went from 7 to 10. That category is still filling its 30-day observation window: 2 days of observed history at the previous scan, 3 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-07-28 (score 61, +1)

No change was recorded against any check on this day. Stability & Change Management went from 3 to 7. That category is still filling its 30-day observation window: 1 days of observed history at the previous scan, 2 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-07-27 (score 60, 0)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-26 (score 60)

First indexed and scored.

## MCP tools (6)

### `verify_claim` (~239 tokens)

Verify a factual claim and return a verdict, confidence score, and cited
sources. Classifies the claim's domain (company / finance / patents /
regulation), cross-references web search and the relevant FoundryNet data
network source, and returns a verdict (supported | disputed | unverifiable)
with a 0-100 confidence, the cited sources, and a short explanation. Results
carry a verifiable provenance attestation and are cached for 24h.

PAID: $0.02 per verification after a daily free allowance (10/day). On a
402, pay the returned payment challenge and re-call with the SAME args plus
payment_tx=<signature>. agent_id scopes your allowance; an Authorization:
Bearer fnet_ key bypasses it.

Input parameters:

- `agent_id`: stable id for your agent (scopes the free-tier counter).
- `claim` (string, required): the factual statement to verify, e.g. "Acme Corp was founded in 2009".
- `context`: optional extra context that disambiguates the claim.
- `payment_tx`: payment transaction signature, when re-calling after a 402.

### `batch_verify` (~201 tokens)

Verify many factual claims in one batch fact-check call. Returns an array of
verify_claim results (verdict + confidence + cited sources + explanation),
each cross-referencing web search and the FoundryNet data network, plus the
batch pricing and a verifiable provenance attestation over the whole batch. Each
claim is cached for 24h, so repeats are cheap.

PAID: $0.01 per claim, minimum $0.05 per batch, after the daily
free allowance (10/day). On a 402, pay the returned payment challenge and re-call
with the SAME args plus payment_tx=<signature>. An Authorization: Bearer
fnet_ key bypasses it.

Input parameters:

- `agent_id`: stable id for your agent (scopes the free-tier counter).
- `claims` (array, required): array of claim strings (1-50).
- `payment_tx`: payment transaction signature, when re-calling after a 402.

### `source_check` (~183 tokens)

Check a source URL's credibility and trustworthiness for source verification
— domain age (via RDAP), trust signals, bias indicators, and publication
history. Use it to weight whether a citation is trustworthy. Results carry a
verifiable provenance attestation and are cached for 24h.

PAID: $0.01 per check after the daily free allowance (10/day). On a 402,
pay the returned payment challenge and re-call with the SAME args plus
payment_tx=<signature>. An Authorization: Bearer fnet_ key bypasses it.

Input parameters:

- `agent_id`: stable id for your agent (scopes the free-tier counter).
- `payment_tx`: payment transaction signature, when re-calling after a 402.
- `url` (string, required): the source URL or domain to assess, e.g. "https://reuters.com/...".

### `daily_brief` (~241 tokens)

Get the curated daily fact-check brief — the day's claim-verification signals
in one package: the top disputed claims, the most-verified claims, the
trending topics being checked, and counts by verdict + domain. Each brief carries a
verifiable provenance attestation so a buyer can verify it was produced by this
server, unaltered.

PAID: $5 per brief. Defaults to today (UTC); a brief expires at the next
midnight UTC. On a 402, pay the returned payment challenge and re-call with the SAME
args plus payment_tx=<signature>. An Authorization: Bearer fnet_ key bypasses
payment.

Input parameters:

- `agent_id`: stable id for your agent (scopes the free-tier counter).
- `date`: brief date YYYY-MM-DD (default today, UTC).
- `payment_tx`: payment transaction signature, when re-calling after a 402.
- `stripe_token`: Stripe Checkout Session id (cs_…), when re-calling after paying the Stripe payment link (alternative to x402). Can also be supplied via the X-Stripe-Token header.

### `brief_summary` (~165 tokens)

Get the top 5 signals from today's brief as structured JSON — a cheap
sample of the full daily_brief. Returns the day's highest-priority items
(no prose) so an agent can decide whether to buy the full brief.

PAID: $0.50 (vs the full daily_brief price). Defaults to today (UTC).
On a 402, pay the returned payment challenge and re-call with the SAME args plus
payment_tx=<signature>. An Authorization: Bearer fnet_ key bypasses payment.

Input parameters:

- `agent_id`: stable id for your agent (scopes the free-tier counter).
- `date`: brief date YYYY-MM-DD (default today, UTC).
- `payment_tx`: payment transaction signature, when re-calling after a 402.

### `mint_info` (~96 tokens)

Get FoundryNet Data Network info + provenance attestation details. FREE.

Returns how to attach a verifiable provenance attestation to your agent's
fact-verification results, plus the sister data servers across the full
FoundryNet Data Network (financial-signals, cyber-intel, patent-intel,
gov-contracts, compliance, brand-intel, weather-intel, academic-intel,
oss-intel, social-intel).

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/foundrynet-fact-check-mcp/fact-check-mcp-production#diagnostics

## Score history

- 2026-08-04: 50
- 2026-08-03: 50
- 2026-08-02: 50
- 2026-08-01: 62
- 2026-07-31: 62
- 2026-07-30: 62
- 2026-07-29: 62
- 2026-07-28: 61
- 2026-07-27: 60
- 2026-07-26: 60

## Links

- Remote endpoint: https://fact-check-mcp-production.up.railway.app/mcp
- Repository: https://github.com/FoundryNet/fact-check-mcp
- Changelog RSS feed: https://verifymcp.io/servers/foundrynet-fact-check-mcp/fact-check-mcp-production/changelog.xml
- Changelog JSON feed: https://verifymcp.io/servers/foundrynet-fact-check-mcp/fact-check-mcp-production/changelog.json
- HTML version of this page: https://verifymcp.io/servers/foundrynet-fact-check-mcp/fact-check-mcp-production