# Cybersecurity Threat Intelligence MCP (remote · cyber-intel-mcp-production.up.railway.app)

CVE search, vulnerability database, EPSS exploit prediction, KEV, IP reputation & threat feed.

- Trust score: 61/100 (medium)
- Change this week: 0
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-04

## Components

- remote · `cyber-intel-mcp-production.up.railway.app`: 61/100 (this document), [markdown](https://verifymcp.io/servers/foundrynet-cyber-intel-mcp/cyber-intel-mcp-production.md), [page](https://verifymcp.io/servers/foundrynet-cyber-intel-mcp/cyber-intel-mcp-production)

## Channel facts

- Endpoint: `https://cyber-intel-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-cyber-intel-mcp https://cyber-intel-mcp-production.up.railway.app/mcp
```

### Codex

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

### opencode

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

### OpenClaw

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

### Hermes

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

### Other

```json
{
  "mcpServers": {
    "foundrynet-cyber-intel-mcp": {
      "type": "http",
      "url": "https://cyber-intel-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.

### 2026-08-01 (score 61, 0)

- [security regression] Endpoint reachability: reachable → unreachable

### 2026-07-31 (score 61, 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 61, 0)

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

### 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, +1)

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

### 2026-07-26 (score 59)

First indexed and scored.

## MCP tools (9)

### `search_cve` (~302 tokens)

Search CVEs in the vulnerability database by keyword, CVSS severity/score,
EPSS exploit-prediction likelihood, attack vector, recency, or CISA KEV
status. Returns CVSS, EPSS, KEV flag, and affected products, newest first.
Threat intel from NVD, EPSS, CISA KEV, and GHSA.

PAID: $0.01 per query after a daily free allowance (25/day). On a 402,
settle the returned payment request and re-call with the SAME args plus
payment_tx=<reference>. 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).
- `attack_vector`: network | adjacent | local | physical.
- `days_back`: only CVEs published in the last N days.
- `is_kev`: true → only CISA Known-Exploited Vulnerabilities.
- `keyword`: text matched against the CVE description.
- `limit` (integer): max rows (1-200, default 50).
- `min_cvss`: minimum CVSS v3 base score (0-10).
- `min_epss`: minimum EPSS exploit probability (0-1).
- `payment_tx`: payment transaction reference, when re-calling after a 402.
- `severity`: critical | high | medium | low.

### `cve_detail` (~109 tokens)

Get the full record for a single CVE from the vulnerability database —
CVSS v3 breakdown (score/severity/vector/attack vector/complexity), EPSS
exploit-prediction probability + percentile, CISA KEV status + due date,
CWE, affected products, and references. Sources: NVD, EPSS, CISA KEV, GHSA.
FREE.

Input parameters:

- `cve_id` (string, required): e.g. "CVE-2021-44228".

### `check_ip` (~150 tokens)

Check IP reputation — abuse reports, threat type, confidence, ISP, and
OTX pulse associations for an IP. Threat intel combining AbuseIPDB and
AlienVault OTX.

PAID: $0.01 per query after the daily free allowance (25/day). On a
402, settle the returned payment request and re-call with the SAME args plus
payment_tx=<reference>. An Authorization: Bearer fnet_ key bypasses it.

Input parameters:

- `agent_id`: stable id for your agent (scopes the free-tier counter).
- `ip_address` (string, required): the IPv4 address to check.
- `payment_tx`: payment transaction reference, when re-calling after a 402.

### `check_domain` (~146 tokens)

Check domain reputation — threat indicators, OTX pulse associations, and
threat classification for a domain. Threat intel from AlienVault OTX.

PAID: $0.01 per query after the daily free allowance (25/day). On a
402, settle the returned payment request and re-call with the SAME args plus
payment_tx=<reference>. An Authorization: Bearer fnet_ key bypasses it.

Input parameters:

- `agent_id`: stable id for your agent (scopes the free-tier counter).
- `domain` (string, required): the domain to check, e.g. "example.com".
- `payment_tx`: payment transaction reference, when re-calling after a 402.

### `vulnerability_scan` (~207 tokens)

Scan a product/vendor/CPE for all known vulnerabilities, sorted by EPSS
exploit-prediction likelihood with CISA KEV flags — the "should I be worried
about this dependency?" security scanning tool. Threat intel from NVD, EPSS,
CISA KEV, and GHSA. Premium.

PAID: $0.02 per query after the daily free allowance (25/day). On a
402, settle the returned payment request and re-call with the SAME args plus
payment_tx=<reference>. An Authorization: Bearer fnet_ key bypasses it.

Input parameters:

- `agent_id`: stable id for your agent (scopes the free-tier counter).
- `cpe`: a CPE string to match exactly.
- `payment_tx`: payment transaction reference, when re-calling after a 402.
- `product_name`: product/library/software name, e.g. "log4j".
- `vendor`: vendor name, e.g. "apache".

### `threat_feed` (~201 tokens)

Pull the recent threat-intelligence feed — real-time threat indicators
(IPs, domains, hashes, URLs) from AlienVault OTX pulses and reputation
checks, filterable by type, threat, confidence, and recency.

PAID: $0.01 per query after the daily free allowance (25/day). On a
402, settle the returned payment request and re-call with the SAME args plus
payment_tx=<reference>. An Authorization: Bearer fnet_ key bypasses it.

Input parameters:

- `agent_id`: stable id for your agent (scopes the free-tier counter).
- `hours_back`: only indicators seen in the last N hours.
- `indicator_type`: ip | domain | hash | url.
- `min_confidence`: minimum confidence 0-100.
- `payment_tx`: payment transaction reference, when re-calling after a 402.
- `threat_type`: malware | phishing | botnet | scanner | spam.

### `daily_brief` (~275 tokens)

Get the curated daily threat-intelligence brief — the day's most
significant signals in one package: critical CVEs with high EPSS
exploit-prediction, new CISA KEV additions, the most-exploitable
vulnerabilities, and active threat indicators. Threat intel from NVD, CISA
KEV, EPSS, GHSA, AbuseIPDB, and OTX. Each brief carries verifiable
provenance so a buyer can confirm it was produced by this server, unaltered.

PAID: $15 per brief. Defaults to today (UTC); a brief expires at the
next midnight UTC. On a 402, settle the returned payment request and re-call with
the SAME args plus payment_tx=<reference>. 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 reference, when re-calling after a 402.
- `stripe_token`: Stripe Checkout Session id (cs_…), when re-calling after paying the Stripe payment link (alternative to the metered rail). Can also be supplied via the X-Stripe-Token header.

### `brief_summary` (~169 tokens)

Get the top 5 signals from today's threat 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 $15 for the full daily_brief). Defaults to today (UTC).
On a 402, settle the returned payment request and re-call with the SAME args plus
payment_tx=<reference>. 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 reference, when re-calling after a 402.

### `mint_info` (~89 tokens)

Get FoundryNet Data Network info and result-provenance details. FREE.

Returns how this server attaches verifiable provenance to your agent's
security/threat-intelligence analysis, plus the sister data servers
(gov-contracts, brand-intel, patent-intel, financial-signals, weather-intel,
compliance, academic-intel, fact-check, oss-intel, social-intel).

## Diagnostics

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

## Score history

- 2026-08-04: 61
- 2026-08-03: 61
- 2026-08-02: 61
- 2026-08-01: 61
- 2026-07-31: 61
- 2026-07-30: 61
- 2026-07-29: 61
- 2026-07-28: 61
- 2026-07-27: 60
- 2026-07-26: 59

## Links

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