# TenderCrest AI (remote · www.tendercrestai.com)

Evidence-backed RFP responses, reviewed together.

- Trust score: 76/100 (medium)
- Change this week: +4
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-21

## Components

- remote · `www.tendercrestai.com`: 76/100 (this document), [markdown](https://verifymcp.io/servers/tendercrestai-tendercrest-ai/www.md), [page](https://verifymcp.io/servers/tendercrestai-tendercrest-ai/www)

## Channel facts

- Endpoint: `https://www.tendercrestai.com/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `0.1.0`

## 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 2026-11-21.

- **Endpoint Security**: 80/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - No authorisation is required to call this server. Nothing on it is marked destructive, but we can't show that an anonymous caller can only read: full credit needs the server to list at least one tool and every tool to be verifiably read-only. We use a best-effort check of tool names and descriptions to tell read-only tools from tools that change things, so some genuinely read-only tools may not get full credit. Names that start with a read verb (get, list, read, search and similar) and accurate readOnlyHint annotations help. Meet that to earn full credit, or require authorisation.
  - HTTPS is enforced; there's no plaintext access path.
  - The HSTS (Strict-Transport-Security) header is present.
  - 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**: 76/100
  - AI-judged instruction clarity (good).
  - Tool/resource definitions use about 1363 tokens (~97/item across 14 items; 14 tools + 0 resources), lean.
  - 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**: 96/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 88% of tool parameters carry a description.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 14 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 15 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 60/100
  - Spec-recency check failed: implements MCP spec 2025-06-18; the latest is 2026-07-28.

## Install

### How do I install the TenderCrest AI MCP server?

TenderCrest AI is a hosted endpoint at https://www.tendercrestai.com/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add --transport http tendercrestai-tendercrest-ai 'https://www.tendercrestai.com/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "tendercrestai-tendercrest-ai": {
      "url": "https://www.tendercrestai.com/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "tendercrestai-tendercrest-ai": {
      "type": "http",
      "url": "https://www.tendercrestai.com/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.tendercrestai-tendercrest-ai]
url = "https://www.tendercrestai.com/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "tendercrestai-tendercrest-ai": {
      "type": "remote",
      "url": "https://www.tendercrestai.com/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add tendercrestai-tendercrest-ai --url 'https://www.tendercrestai.com/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  tendercrestai-tendercrest-ai:
    url: "https://www.tendercrestai.com/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "tendercrestai-tendercrest-ai": {
      "Transport": "http",
      "Url": "https://www.tendercrestai.com/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add tendercrestai-tendercrest-ai -t streamable-http -u 'https://www.tendercrestai.com/mcp'
```

### Other

```json
{
  "mcpServers": {
    "tendercrestai-tendercrest-ai": {
      "type": "http",
      "url": "https://www.tendercrestai.com/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.

### 2026-11-21 (score 76, +1)

No change was recorded against any check on this day. Stability & Change Management went from 23 to 27. That category is still filling its 30-day observation window: 7 days of observed history at the previous scan, 8 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-20 (score 75, 0)

- [security] Tool “shred_rfp” rewrote its description, which is the text the model reads
- [cosmetic] “check_bid_fit” reworded the description of “text”
- [cosmetic] “shred_rfp” reworded the description of “text”

### 2026-11-19 (score 75, +1)

No change was recorded against any check on this day. Stability & Change Management went from 17 to 20. That category is still filling its 30-day observation window: 5 days of observed history at the previous scan, 6 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-17 (score 74, +1)

No change was recorded against any check on this day. Stability & Change Management went from 10 to 13. That category is still filling its 30-day observation window: 3 days of observed history at the previous scan, 4 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-15 (score 73, +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.

### 2026-11-14 (score 72, 0)

- [functional improvement] Stability: unverified → 0.03

### 2026-11-13 (score 72)

First indexed and scored.

## MCP tools (14)

### `shred_rfp` (~181 tokens)

Shred an RFP

Shred an RFP or solicitation into a numbered requirement list with a gap preview. Paste text or upload a PDF or DOCX. AI extraction can miss requirements and every requirement needs human review. This starts an analysis job and returns a result token; call get_shred_result with the token to read the requirements. Free, no sign-in. Limited to 5 shreds per day, shared with the web shredder.

Input parameters:

- `file` (object)
- `processingConsent` (boolean, required): Must be true: confirms the source may be processed to extract requirements.
- `source` (string): Where the solicitation came from, up to 500 characters.
- `text` (string): Solicitation text, 40 to 300000 characters. Provide text or file.
- `title` (string): Short title for the solicitation, up to 200 characters.

### `get_shred_result` (~78 tokens)

Read a shred result

Read the result of a shred_rfp job using its result token. Returns the status and, when complete, the numbered requirements, the gap preview, and any warnings. Free, no sign-in.

Input parameters:

- `resume` (boolean): Set true to restart a stalled job.
- `token` (string, required): Result token returned by shred_rfp.

### `check_bid_fit` (~197 tokens)

Check bid fit

Run a bid/no-bid fit check on a solicitation: five questions scored 0 to 2, for a fit read of Strong fit, Worth a closer look, or Likely pass. This is a fit score, never a win prediction. Needs the solicitation text or file plus a short title, source, and the five answers. Starts an analysis job and returns a result token; call get_bid_check_result with the token to read the verdict. Free, no sign-in.

Input parameters:

- `answers` (object, required)
- `file` (object)
- `processingConsent` (boolean, required): Must be true: confirms the source may be processed.
- `source` (string, required): Where the solicitation came from, up to 500 characters.
- `text` (string): Solicitation text, 40 to 300000 characters. Provide text or file.
- `title` (string, required): Short title for the bid, up to 200 characters.

### `get_bid_check_result` (~90 tokens)

Read a bid check result

Read the result of a check_bid_fit job using its result token. Returns the status and, when complete, the fit verdict, the score out of 10, the factor breakdown, the top reasons, and the top gaps. Free, no sign-in.

Input parameters:

- `resume` (boolean): Set true to restart a stalled job.
- `token` (string, required): Result token returned by check_bid_fit.

### `search_opportunities` (~165 tokens)

Search SAM.gov opportunities

Search live SAM.gov federal opportunities from the past 364 days. Returns up to 25 notices per page with title, agency, deadline, NAICS, PSC, set-aside, and the canonical SAM.gov link. Federal notices only; no contract value bands are published. Free, no sign-in. Limited to 10 searches per day, shared with the web feed.

Input parameters:

- `keyword` (string): Keyword search, up to 100 characters.
- `naics` (string): 6-digit NAICS code.
- `page` (integer): Results page, 0 to 9. Default 0.
- `psc` (string): 4-character product service code.
- `setAside` (string): Set-aside type code, up to 12 characters.

### `get_opportunity` (~72 tokens)

Read a SAM.gov opportunity

Read one SAM.gov opportunity by its notice URL or 32-character notice ID, including the notice description text when SAM.gov returns it. Descriptions are not complete solicitation packages; attachments are not imported. Free, no sign-in.

Input parameters:

- `notice` (string, required): SAM.gov notice URL or 32-character notice ID.

### `list_organizations` (~35 tokens)

List organizations

List the knowledge organizations (company evidence libraries) the signed-in TenderCrest user belongs to. Needs a TenderCrest account.

### `list_evidence` (~61 tokens)

List evidence

List the signed-in user's own company evidence for one organization: uploaded source documents and saved answers with their approval state. Only returns evidence the user's organization owns. Needs a TenderCrest account.

Input parameters:

- `orgId` (string, required): Organization ID from list_organizations.

### `read_evidence_source` (~64 tokens)

Read an evidence source

Read one evidence source document and its extracted text chunks, for the signed-in user's own organization. Needs a TenderCrest account.

Input parameters:

- `documentId` (string, required): Document ID from list_evidence.
- `orgId` (string, required): Organization ID from list_organizations.

### `search_evidence` (~76 tokens)

Search evidence

Search the signed-in user's own company evidence for one organization by meaning, using the same semantic search as the web app. Returns matching evidence with citations. Needs a TenderCrest account.

Input parameters:

- `orgId` (string, required): Organization ID from list_organizations.
- `query` (string, required): Search text, up to 2000 characters.

### `list_proposals` (~67 tokens)

List proposals

List the signed-in TenderCrest user's own proposals (projects), newest first. Needs a TenderCrest account.

Input parameters:

- `page` (integer): Results page, 0 to 1000. Default 0.
- `query` (string): Title search, up to 200 characters.

### `read_proposal` (~66 tokens)

Read a proposal

Read one of the signed-in user's own proposals in full: project state, sections, requirements, evidence decisions, jobs, files, activity, approvals, and readiness. Read-only. Needs a TenderCrest account.

Input parameters:

- `projectId` (string, required): Proposal ID from list_proposals.

### `list_proposal_records` (~87 tokens)

List proposal records

List saved records for one of the signed-in user's own proposals: jobs, files, activity, notifications, assessments, or approvals. Read-only. Needs a TenderCrest account.

Input parameters:

- `kind` (string, required)
- `page` (integer): Results page, 0 to 1000. Default 0.
- `projectId` (string, required): Proposal ID from list_proposals.

### `get_proposal_revision` (~60 tokens)

Read a proposal revision

Read one saved revision of the signed-in user's own proposal. Read-only. Needs a TenderCrest account.

Input parameters:

- `projectId` (string, required): Proposal ID from list_proposals.
- `revision` (integer, required): Revision number, 0 or higher.

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/tendercrestai-tendercrest-ai/www#diagnostics

## Score history

- 2026-11-21: 76
- 2026-11-20: 75
- 2026-11-19: 75
- 2026-11-18: 74
- 2026-11-17: 74
- 2026-11-16: 73
- 2026-11-15: 73
- 2026-11-14: 72
- 2026-11-13: 72

## Common questions

### What is the TenderCrest AI MCP server?

TenderCrest AI is an MCP server listed in the public MCP registry as io.github.tendercrestai/tendercrest-ai. Evidence-backed RFP responses, reviewed together. This page covers its hosted endpoint (https://www.tendercrestai.com/mcp).

### Is the TenderCrest AI MCP server safe to use?

TenderCrest AI scores 76 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the TenderCrest AI MCP server expose?

TenderCrest AI exposes 14 tools: shred_rfp, get_shred_result, check_bid_fit, get_bid_check_result, search_opportunities, and 9 more. Their descriptions and schemas cost roughly 1,299 tokens of context every time the server is loaded.

### Does the TenderCrest AI MCP server require authentication?

No. We connected to TenderCrest AI without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

### Is the TenderCrest AI MCP server still maintained?

TenderCrest AI is still listed as active in the MCP registry. We last reached this channel on 21 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

### What did VerifyMCP test on the TenderCrest AI MCP server?

VerifyMCP ran 13 checks on TenderCrest AI, covering TLS certificate, Authorization, HTTPS, HSTS header and 9 more. Supply Chain Security and Provenance & Transparency do not apply to a hosted endpoint, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.

## Links

- Remote endpoint: https://www.tendercrestai.com/mcp
- Repository: https://github.com/tendercrestai/tendercrestai
- Website: https://www.tendercrestai.com/
- Changelog RSS feed: https://verifymcp.io/servers/tendercrestai-tendercrest-ai/www.xml
- Changelog JSON feed: https://verifymcp.io/servers/tendercrestai-tendercrest-ai/www/changelog.json
- Trust report (JSON): https://verifymcp.io/servers/tendercrestai-tendercrest-ai/www.json
- HTML version of this page: https://verifymcp.io/servers/tendercrestai-tendercrest-ai/www
