🧰 Procurement Evidence MCP Server

Locate the public procurement record behind a claim, across the UK, the EU and the US. Every row carries the awarding body's own record id and a direct public URL, so "who won this contract" is checkable at source.

An evidence locator, not an analyst. It does not score suppliers, rank bids, or infer relationships between contracts — it tells you which record to open.

This is a standby MCP server: it stays warm on Apify and answers tool calls from any MCP client (Claude Desktop, Cursor, an agent framework) at https://nexgenwatch--procurement-evidence-mcp.apify.actor/mcp. Billing is pay-per-event: $0.05 when the server starts, then $0.05 per tool call (mcp-tool-call). Source: api.ted.europa.eu, api.usaspending.gov, www.find-tender.service.gov.uk.

No login, no source API key and no CAPTCHA solving are involved: the source is read logged-out.

📊 Sample Output

A standby server answers tool calls rather than writing a dataset, so the sample is the server's own live health answer (GET https://nexgenwatch--procurement-evidence-mcp.apify.actor/, HTTP 200, read on 2026-09-17) followed by its tool table:

{
  "server": "procurement-evidence",
  "billing_gate": true,
  "declared_events": [
    "apify-actor-start",
    "mcp-tool-call"
  ],
  "jurisdictions": [
    "EU",
    "UK",
    "US"
  ],
  "rate_limit_per_sec": 5.0,
  "rate_waits": 0,
  "ready": true
}

Tool	Arguments	What it returns
list_jurisdictions	``	Which procurement systems this server covers and what each can answer. Read this before relying on a cross-jurisdiction search — the three sources do not carry the same fields.
search_procurement	`text: str	None = None, jurisdictions: list[str]
search_by_supplier	`supplier: str, jurisdictions: list[str]	None = None, since: str
get_record_url	jurisdiction: str, record_id: str	Turn a record id into its official public URL, without fetching. Use the jurisdiction and record_id returned by the search tools.

✅ What you get

4 tools, each returning a JSON object built only from what the source answered. A lookup the source answers with 'not found' is a sourced answer (charged); malformed input or a source failure returns a notice that is NOT charged; nothing is ever fabricated.

Tools

tool	what it answers
list_jurisdictions	What is covered and what each source can actually tell you. Read this first.
search_procurement	Notices and awards across all three systems, each with an official URL
search_by_supplier	Contracts associated with a named supplier, with the match basis stated
get_record_url	Turn a record id into its official URL

Sources — public, logged-out, no key

jurisdiction	source	what it carries
UK	Find a Tender Service (OCDS)	notices and award values
EU	Tenders Electronic Daily (TED)	the notice and its official URL — not award values inline
US	USAspending	federal contract awards with amounts and recipients (types A–D, not grants)

The three do not answer the same question equally well, and every response says so. A cross-jurisdiction search reports which systems were searched, which failed, and coverage_complete — because a "no results" produced by a partial search is the failure that would matter most here.

UK Contracts Finder was probed live and works; it is deliberately not wired, because it covers the same jurisdiction as Find a Tender and two overlapping UK sources would be duplication rather than coverage. It is the natural addition if below-threshold UK notices are wanted.

Match honesty on supplier search

• US matches are the awarding system's own recipient field.
• UK / EU matches are name occurrences in the record. A match resting only on a title is returned with requires_human_review: true and labelled a candidate.

There is no similarity score. A number would read as a probability and it is not one.

Pacing

None of these three publish a hard request cap, so there is no number to comply with — but a standby server answering several agents at once can still hammer a public service. Every outbound call goes through one shared token bucket at 5 requests/second with strict pacing (burst 1), the shape ratified in Section 3: a bucket that starts full passes its whole capacity instantly, and the burst is the moment that matters.

⚙️ Sample inputs

1. Connect an MCP client (Claude Desktop / Cursor style config; your Apify API token goes in the header):

{
  "mcpServers": {
    "procurement-evidence-mcp": {
      "url": "https://nexgenwatch--procurement-evidence-mcp.apify.actor/mcp",
      "headers": {
        "Authorization": "Bearer <YOUR_APIFY_TOKEN>"
      }
    }
  }
}

2. One tool call over JSON-RPC (what the client sends to /mcp; each call is one mcp-tool-call event):

{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "list_jurisdictions",
    "arguments": {}
  }
}

3. Health check from a shell (free — no tool call is charged):

$curl -H "Authorization: Bearer $APIFY_TOKEN" https://nexgenwatch--procurement-evidence-mcp.apify.actor/

🧾 JSON sample record

The live health record above is the server's own answer; a tool result carries the fields listed in the tool table plus scope and note.

🔧 How it works

Source. api.ted.europa.eu, api.usaspending.gov, www.find-tender.service.gov.uk — endpoints: https://api.ted.europa.eu/v3/notices/search, https://api.usaspending.gov/api/v2/search/spending_by_award/, https://www.find-tender.service.gov.uk/api/1.0/ocdsReleasePackages. Public, logged-out reads only.

Standby. Apify keeps one server process warm; each MCP session is served by that process and idle servers are stopped by the platform. Nothing is cached between calls except what the source itself caches.

Charging. Every tool call charges one mcp-tool-call at $0.05 through Apify's pay-per-event billing before the answer is returned; the declared events are asserted against the live pricing at startup (billing_gate in the health answer).

What is not done. No login, no CAPTCHA bypass, no private data, no scraping of pages the source does not publish to any visitor.

💰 Pricing example

Event	Free	Bronze	Silver	Gold
Actor Start (apify-actor-start)	$0.05	$0.05	$0.05	$0.05
Tool call (mcp-tool-call)	$0.05	$0.05	$0.05	$0.05

• 10 tool calls in one session: $0.05 start + 10 × $0.05 = $0.55
• 100 tool calls in one session: $0.05 start + 100 × $0.05 = $5.05
• 1000 tool calls in one session: $0.05 start + 1000 × $0.05 = $50.05

A health check or a connection that makes no tool call charges only the $0.05 start fee. A sourced 'not found' answer is a completed tool call and is charged; a notice for malformed input or a source failure is not charged (settle() charges only chargeable outcomes).

⚖️ Legal & ToS

The server reads public data published by api.ted.europa.eu, api.usaspending.gov, www.find-tender.service.gov.uk to any visitor, identifies itself, and does not access accounts or private data. Use the answers in line with the source's terms and your local law; the intended use is B2B research and agent tooling.

❓ FAQ

Q: Do I need a source API key?
A: No. api.ted.europa.eu, api.usaspending.gov, www.find-tender.service.gov.uk is read logged-out. You need only your Apify API token to connect to the server.

Q: Which MCP clients work?
A: Any client that speaks the MCP HTTP transport: Claude Desktop, Cursor, Windsurf, LangChain/LlamaIndex MCP adapters and Apify's own MCP client. Point it at the /mcp URL above.

Q: What happens when the source has no answer?
A: A sourced 'not found' (for example a 404 for an unknown identifier) comes back as an answer with scope and note explaining what was checked (where the server carries those fields), and is charged as a completed call; malformed input or a source outage returns a notice that is not charged. Nothing is invented.

Q: How is a call billed?
A: One mcp-tool-call event per tool call at $0.05, plus $0.05 when the server starts. Idle time is not billed to you.

Q: Is it rate limited?
A: The server paces requests to the source (RATE_PER_SEC=5.0) and answers calls in the order they arrive.

Q: Can I call it without an MCP client?
A: Yes — the /mcp endpoint is plain JSON-RPC over HTTP (sample input 2), and GET / is a free health check.

🆘 Troubleshooting

• 401 / 403 from the server → the Authorization header is missing or the token is wrong → use Bearer <your Apify API token>.
• 400 Missing session ID → the client hit /mcp without initialising an MCP session → let the MCP client connect (it performs the handshake); raw JSON-RPC needs the session header the initialise call returns.
• Tool returns a notice instead of data → the input was malformed or empty, or the source failed → the call was not charged; check the note/reason field, fix the input and call again.
• First call is slow → the standby server was cold and Apify started it → later calls in the same session are fast.

🔗 Related Actors

• Federal Rule Impact MCP Server — Answer 'what regulations changed for this industry' from the US Federal Register: search and retrieve rules, proposed rules and notices by CFR title,…
• Grants Qualification MCP Server — Report what a US federal grant agency actually states about who may apply, and screen an applicant type against it. Three outcomes, and 'qualified' i…
• Official Travel Advice MCP Server — MCP server for UK FCDO foreign travel advice from the official GOV.UK Content API — safety warnings, entry and health requirements, and update histor…
• Research Funding Landscape MCP Server — Answer 'who funds research on this topic' across two public government registers: US National Science Foundation awards and UK Research and Innovatio…
• SEC Filing Evidence MCP Server — Locate the SEC filing behind a claim. Every answer carries the accession number, the filing date and a direct SEC URL, so an agent's claim about a pu…
• Trademark Dispute MCP Server — Answer 'has anyone contested a mark like this' across the USPTO Trademark Trial and Appeal Board and the Canadian Trademarks Opposition Board. Report…
• 🏢 About NexGenData — NexGen Watch is NexGenData's fleet of 256 public monitoring and lookup actors built on official sources, pay-per-result. Browse the catalog at apify.com/nexgenwatch.

⭐ Found this useful?

If this server answered a question your agent could not, a quick review on the Apify Store helps other teams find it. Feature request or a source that changed? Open it from the Issues tab — every one is read.