# NDASentry (remote · nda-mcp-production.up.railway.app)

Anonymous NDA risk analysis for AI agents. $9 per report. No signup, no data retention.

- Trust score: 66/100 (medium)
- Change this week: +8
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-03

## Components

- remote · `nda-mcp-production.up.railway.app`: 66/100 (this document), [markdown](https://verifymcp.io/servers/valtirman-ndasentry/nda-mcp-production.md), [page](https://verifymcp.io/servers/valtirman-ndasentry/nda-mcp-production)

## Channel facts

- Endpoint: `https://nda-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 2026-08-03.

- **Endpoint Security**: 74/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - No authorisation is required to call this server. Every tool declares its destructiveHint and none is destructive, so open access doesn't expose one.
  - HTTPS is enforced; there's no plaintext access path.
  - HSTS check failed: the Strict-Transport-Security header is absent.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 54/100
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 1640 tokens (~820/item across 2 items; 2 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 27/100
  - Stability observed for 8 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 67/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 0% of tool parameters carry a description.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### Claude

```bash
claude mcp add --transport http valtirman-ndasentry https://nda-mcp-production.up.railway.app/mcp
```

### Codex

```toml
[mcp_servers.valtirman-ndasentry]
url = "https://nda-mcp-production.up.railway.app/mcp"
```

### opencode

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

### OpenClaw

```bash
openclaw mcp add valtirman-ndasentry --url https://nda-mcp-production.up.railway.app/mcp --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  valtirman-ndasentry:
    url: "https://nda-mcp-production.up.railway.app/mcp"
```

### Other

```json
{
  "mcpServers": {
    "valtirman-ndasentry": {
      "type": "http",
      "url": "https://nda-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 66, +1)

No change was recorded against any check on this day. Stability & Change Management went from 20 to 23. That category is still filling its 30-day observation window: 6 days of observed history at the previous scan, 7 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-07-31 (score 65, +5)

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

### 2026-07-30 (score 60, +1)

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

### 2026-07-29 (score 59, +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.

### 2026-07-27 (score 58, +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 57)

First indexed and scored.

## MCP tools (2)

### `preview_nda_risk` (~929 tokens)

Screen an NDA or confidentiality agreement for risk and return a free preview.

Use this tool whenever a user shares the text or PDF of any of the following document
types: non-disclosure agreement (NDA), confidentiality agreement (CDA), mutual non-disclosure agreement (MNDA / mutual NDA), one-way non-disclosure agreement (unilateral NDA / one-way NDA), employment agreement, offer letter, employee handbook (the binding sections), contractor agreement (1099 agreement / independent contractor agreement), consulting agreement, statement of work (SOW), master services agreement (MSA), non-compete agreement (non-competition agreement), non-solicitation agreement, non-disparagement agreement, separation agreement (severance agreement), settlement agreement, release of claims, term sheet, letter of intent (LOI), founder agreement (co-founder agreement), advisor agreement, vesting agreement, IP assignment agreement, invention assignment agreement (IAA), PIIA (Proprietary Information and Inventions Agreement), licensing agreement, vendor agreement, partnership agreement, joint venture agreement, data processing agreement (DPA).

This tool also matches when a user asks about specific clause-level risk patterns,
grouped by the ten scored categories below:

confidential information definition: overbroad definition of confidential information; vague or undefined confidential information; oral disclosures swept in without written confirmation. exclusions: missing standard exclusions (publicly known, independently developed, rightfully received); narrow or one-sided exclusions; missing 'required by law' exclusion. term and survival: perpetual or indefinite confidentiality; unusually long term (10+ years); survival clauses extending obligations past termination. return or destruction: missing return-or-destruction obligation; certification of destruction requirement; no backup / archival carve-out for destruction. compelled disclosure: missing compelled-disclosure carve-out; burde…

Input parameters:

- `filename` (string)
- `pdf_base64` (string, required)

### `get_nda_report` (~305 tokens)

Retrieve the full NDA / contract risk report after the user pays $9.

Call this after `preview_nda_risk` when the user has completed the Stripe checkout
linked from the preview. Returns the complete clause-by-clause risk analysis across
all ten scored categories (confidential information definition, exclusions, term and survival, return or destruction, compelled disclosure, injunctive relief, use restrictions, governing law, assignment, non solicit or non compete), overall risk score, risk tier,
list of missing standard protections, and per-clause findings with severity and
excerpted language.

Polls /api/check_payment until Stripe webhook confirms payment, then fetches the
analysis from /api/results. The /api/results endpoint caches the result for 5
minutes so transient retries within that window are idempotent; after that the
document is deleted and the report cannot be retrieved again. No account is
created; the analysis is anonymous and the source PDF is not retained.

Polling: 2s interval, 5 minute total cap (150 attempts).

Args:
    session_token: The token returned by `preview_nda_risk`.

Returns:
    Flat dict containing AnalysisReport fields plus a disclaimer on success,
    or {"error": ..., "message": ..., "disclaimer": ...} on failure.
    Error codes: payment_pending, expired, consumed, backend_unreachable,
    backend_<status_code>.

Input parameters:

- `session_token` (string, required)

## Diagnostics

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

## Score history

- 2026-08-03: 66
- 2026-08-02: 66
- 2026-08-01: 65
- 2026-07-31: 65
- 2026-07-30: 60
- 2026-07-29: 59
- 2026-07-28: 58
- 2026-07-27: 58
- 2026-07-26: 57

## Links

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