# NextBid — Government Bids for AI (remote · api.nextbid.us)

Search open U.S. federal, state and local government bids and read their documents. Paid; trial.

- Trust score: 85/100 (high trust)
- Change this week: +4
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-04

## Components

- remote · `api.nextbid.us`: 85/100 (this document), [markdown](https://verifymcp.io/servers/us-nextbid-data/api.md), [page](https://verifymcp.io/servers/us-nextbid-data/api)

## Channel facts

- Endpoint: `https://api.nextbid.us/mcp`
- Transports: `streamable-http`
- Auth: `required (not validated)`
- Version: `0.9.37`

## 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 2026-11-04.

- **Endpoint Security**: 89/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation is enforced on tool calls, but the challenge carries no valid RFC 9728 metadata, so a client cannot discover where to get a token.
  - 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**: 63/100
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 1755 tokens (~125/item across 14 items; 14 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 80/100
  - Stability observed for 24 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 80/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 41% 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 14 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### How do I install the NextBid — Government Bids for AI MCP server?

NextBid — Government Bids for AI is a hosted endpoint at https://api.nextbid.us/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 us-nextbid-data 'https://api.nextbid.us/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "us-nextbid-data": {
      "url": "https://api.nextbid.us/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "us-nextbid-data": {
      "type": "http",
      "url": "https://api.nextbid.us/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.us-nextbid-data]
url = "https://api.nextbid.us/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "us-nextbid-data": {
      "type": "remote",
      "url": "https://api.nextbid.us/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add us-nextbid-data --url 'https://api.nextbid.us/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  us-nextbid-data:
    url: "https://api.nextbid.us/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "us-nextbid-data": {
      "Transport": "http",
      "Url": "https://api.nextbid.us/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add us-nextbid-data -t streamable-http -u 'https://api.nextbid.us/mcp'
```

### Other

```json
{
  "mcpServers": {
    "us-nextbid-data": {
      "type": "http",
      "url": "https://api.nextbid.us/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.

### 2026-11-04 (score 85, +1)

No change was recorded against any check on this day. Stability & Change Management went from 77 to 80. That category is still filling its 30-day observation window: 23 days of observed history at the previous scan, 24 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-02 (score 84, +1)

No change was recorded against any check on this day. Stability & Change Management went from 70 to 73. That category is still filling its 30-day observation window: 21 days of observed history at the previous scan, 22 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-31 (score 83, +1)

No change was recorded against any check on this day. Stability & Change Management went from 63 to 67. That category is still filling its 30-day observation window: 19 days of observed history at the previous scan, 20 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-29 (score 82, +1)

No change was recorded against any check on this day. Stability & Change Management went from 57 to 60. That category is still filling its 30-day observation window: 17 days of observed history at the previous scan, 18 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-27 (score 81, +1)

No change was recorded against any check on this day. Stability & Change Management went from 50 to 53. That category is still filling its 30-day observation window: 15 days of observed history at the previous scan, 16 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-25 (score 80, +1)

- [security regression] Authorization: unverified → fail
- [security improvement] Injection markers: unverified → pass
- [security improvement] HSTS header: unverified → pass
- [security improvement] Transport: fail → pass
- [functional improvement] Endpoint reachability: unreachable → reachable
- [functional improvement] Tool coverage: unverified → 100
- [functional improvement] Stability: unverified → 0.47
- [functional improvement] MCP protocol: unverified → pass

### 2026-10-24 (score 79, 0)

- [security regression] Endpoint reachability: reachable → unreachable
- [security regression] Authorization: fail → unverified
- [security regression] Tool safety: pass → unverified
- [security regression] Stability: 0.40 → unverified
- [security regression] HSTS header: pass → unverified
- [security regression] Transport: pass → fail
- [functional regression] Capabilities: pass → unverified
- [functional regression] Tool coverage: 100 → unverified
- [functional] First check of Schema quality: unverified

### 2026-10-22 (score 79, +1)

No change was recorded against any check on this day. Stability & Change Management went from 33 to 37. That category is still filling its 30-day observation window: 10 days of observed history at the previous scan, 11 at this one. The score rises as the window fills, whether or not the server changes.

## MCP tools (14)

### `search_opportunities` (~764 tokens)

Search open government solicitations (SAM.gov, DLA DIBBS, CalProcure, OpenGov, PlanetBids, PublicPurchase, Bonfire, and agency notices syndicated by InstantMarkets) in NextBid's normalized corpus. Returns one deduplicated record per opportunity with agency, deadline, codes, document status and a source link, plus total and facets. Metered on two account meters: one request per call, and each solicitation the first time it reaches the account (repeats are free on that meter). page_size 0 = counts and facets only. Trial: 100 requests and 250 solicitations per account, page_size up to 25. If the solicitation allowance runs out mid-page, delivery.truncated is true and delivery.withheld says how many were held back.

Input parameters:

- `agencies` (array): Agency name fragments, e.g. ["Sacramento", "SMUD"].
- `city` (string): A city (needs states). Keeps only rows tied to it; each row says how in location_match: work_site (place of performance), named_in_title, service_area (needs county), mentioned_in_description (work s…
- `county` (string): A county name without 'County' (needs states), e.g. "Riverside". Matches the record's service area or a county named in the title (service_area) or description (mentioned_in_description).
- `due_within_days` (integer): Only opportunities closing within N days.
- `location_match` (array): Keep only these location tiers (needs city or county). Default: all five.
- `open` (boolean): Default true: only opportunities that are still open. false also returns closed and past-deadline solicitations.
- `page` (integer)
- `page_size` (integer): Results per page (default 25). 0 = counts and facets only. Trial max 25, paid max 100; above the plan max is a 400.
- `q` (string): Keywords (full-text over title and description).
- `set_asides` (array): Set-aside programs from list_set_asides: small_business, 8a, hubzone, sdvosb, wosb, isbee, california_sb_dvbe, open, or any alias ("8(a)", "HUBZone", "DVBE"). Results carry set_aside_basis: designate…
- `sort` (string)
- `sources` (array): Restrict to sources: sam.gov, dibbs, calprocure, opengov, planetbids, publicpurchase, bonfire, instantmarkets.
- `specialties` (array): Your specialties, e.g. ["access control", "surveillance cameras", "fire alarm"]. Never filters: all matches stay; those naming a specialty in the title (2) or description (1) come first, each row lis…
- `states` (array): Two-letter states, e.g. ["CA"]. Matched on the job location (place of performance, service area, buyer state, CalProcure=CA); each result carries a location object with its basis.
- `tradeline_match` (string): validated (default): a trade matches only with NAICS/PSC or text evidence for that trade; loose: tag only (noisier).
- `tradelines` (array): Trade ids or any alias from list_tradelines: e.g. lowvoltage, "access control", "badge readers", "structured cabling", roofing. Omit for all trades.

### `get_opportunity` (~63 tokens)

Full record for one opportunity by NextBid id (NB########): description, AI summary, buyer contacts (current and historical), amendments, filed documents. One request; counts as a delivered solicitation the first time this account receives it.

Input parameters:

- `nb_id` (string, required)

### `list_documents` (~81 tokens)

The document set for one opportunity: source_documents (listed by the source engine: name, size, sha256, source url, whether NextBid stores the original) and nextbid_documents (the current Document 0 and normalized text, readable with read_file). Pipeline artifacts are counted, not listed. Names and metadata only.

Input parameters:

- `nb_id` (string, required)

### `get_document_download` (~70 tokens)

A time-limited download link for one stored original document of an opportunity (sha256 from list_documents, where stored is true). One request; the file is served by NextBid's object store, not through the API.

Input parameters:

- `nb_id` (string, required)
- `sha256` (string, required)

### `get_evidence` (~132 tokens)

The evidence for one opportunity: every indexed document (identity, version, hashes, whether the original is downloadable, whether the AnyDoc extracted text is verified) and the Graphify claims - each a GENERATED label with the SOURCE passage it cites (document, UTF-16 offsets, exact quoted text) and a verification status (RESOLVED = offsets match the hash-verified text and the graph quote). Gaps (pending custody, unavailable extraction, unresolved citations) are listed explicitly. One request.

Input parameters:

- `claims_limit` (integer)
- `claims_offset` (integer)
- `nb_id` (string, required)

### `get_document_text` (~79 tokens)

The AnyDoc extracted text of one document (sha256 = the text sha256 or the original sha256 from get_evidence), verified against its indexed hash. Offsets in get_evidence index into this text. One request.

Input parameters:

- `max_chars` (integer)
- `nb_id` (string, required)
- `sha256` (string, required)

### `list_files` (~78 tokens)

The current stored documents for one opportunity: Document 0 markdown/json and normalized attachment markdown (class document0 / normalized_text). include="all" adds pipeline artifacts (case files, graphs, packets) and superseded Document 0 generations. Use read_file to fetch one.

Input parameters:

- `include` (string)
- `nb_id` (string, required)

### `read_file` (~60 tokens)

Read one stored text artifact of an opportunity (path from list_files). Returns the text, truncated to max_chars (default 60,000).

Input parameters:

- `max_chars` (integer)
- `nb_id` (string, required)
- `path` (string, required)

### `corpus_stats` (~136 tokens)

The corpus numbers with their definitions: total_solicitations (distinct, duplicates excluded), open (listed open by the source with the deadline ahead or unstated, or deadline ahead with no status; passed deadlines and unknown status are separate: listed_open_past_deadline, status_unknown), due_30d (known deadline only), open_set_asides (distinct open solicitations designated under any supported program; each counts once; open competition excluded), open_set_aside_mentions (title language only), set_asides_by_program, unmapped_set_aside_values (for review), open by source, documents, as_of and replica_as_of.

### `list_set_asides` (~89 tokens)

Set-aside and small-business programs NextBid recognizes (federal SBA programs, California SB/DVBE, open competition): id, name, level, what it means, official reference, aliases and today's counts split into open_designated (source-marked) and open_mentioned (title language only). Use an id or alias in search_opportunities.set_asides. Never an eligibility determination.

### `my_account` (~45 tokens)

The account's meter: plan, allowance used and remaining, period reset or trial expiry, keys, what counts as a call, how to upgrade, and the business profile. Free.

### `mark_pursuit` (~71 tokens)

Record that the customer is watching, pursuing, has submitted, won, lost or dropped an opportunity. Call it only when the customer says so; reading a bid is never a pursuit. Free.

Input parameters:

- `nb_id` (string, required)
- `note` (string)
- `status` (string, required)

### `list_tradelines` (~54 tokens)

The trade catalog: each trade id with its name, description, specialties and search aliases, plus today's open count. Use an id or any alias in search_opportunities. Specialties describe supported categories, not open bids.

### `my_usage` (~33 tokens)

The account's meters: requests used and remaining, unique solicitations delivered and remaining, plan period or trial expiry. Free.

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/us-nextbid-data/api#diagnostics

## Score history

- 2026-11-04: 85
- 2026-11-03: 84
- 2026-11-02: 84
- 2026-11-01: 83
- 2026-10-31: 83
- 2026-10-30: 82
- 2026-10-29: 82
- 2026-10-28: 81
- 2026-10-27: 81
- 2026-10-26: 80
- 2026-10-25: 80
- 2026-10-24: 79
- 2026-10-23: 79
- 2026-10-22: 79
- 2026-10-21: 78
- 2026-10-20: 78
- 2026-10-19: 77
- 2026-10-18: 77
- 2026-10-17: 76
- 2026-10-16: 76
- 2026-10-15: 75
- 2026-10-14: 75
- 2026-10-13: 74
- 2026-10-12: 74
- 2026-10-11: 74

## Common questions

### What is the NextBid — Government Bids for AI MCP server?

NextBid — Government Bids for AI is an MCP server listed in the public MCP registry as us.nextbid/data. Search open U.S. federal, state and local government bids and read their documents. Paid; trial. This page covers its hosted endpoint (https://api.nextbid.us/mcp).

### Is the NextBid — Government Bids for AI MCP server safe to use?

NextBid — Government Bids for AI scores 85 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 NextBid — Government Bids for AI MCP server expose?

NextBid — Government Bids for AI exposes 14 tools: search_opportunities, get_opportunity, list_documents, get_document_download, get_evidence, and 9 more. Their descriptions and schemas cost roughly 1,755 tokens of context every time the server is loaded.

### Does the NextBid — Government Bids for AI MCP server require authentication?

Yes. NextBid — Government Bids for AI asked us for credentials when we connected, so you will need to authorise it in your MCP client before it can do anything.

### Is the NextBid — Government Bids for AI MCP server still maintained?

NextBid — Government Bids for AI is still listed as active in the MCP registry. We last reached this channel on 4 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

## Links

- Remote endpoint: https://api.nextbid.us/mcp
- Authorisation metadata: https://api.nextbid.us/.well-known/oauth-protected-resource/mcp
- Website: https://nextbid.us/mcp?ref=mcp-registry
- Changelog RSS feed: https://verifymcp.io/servers/us-nextbid-data/api.xml
- Changelog JSON feed: https://verifymcp.io/servers/us-nextbid-data/api.json
- HTML version of this page: https://verifymcp.io/servers/us-nextbid-data/api