Defense Explorer for Claude
Connect Claude to defence procurement data. Search NSPA, TED and national tenders, rank them against your company profile, and read cited briefs without leaving the conversation.
In short
Add one URL as a custom connector, sign in, and Claude can answer questions about defence tenders with the notice, the score and the quote to back them up.
- 01On claude.ai and Claude Desktop, add a custom connector with the server URL and authorize through OAuth.
- 02In Claude Code, one command adds the server; authenticate from the /mcp menu.
- 03You choose the scopes on the consent page, so a read-only connection is one unticked box away.
Connect in three minutes
[ 03 PATHS ]Claude’s menus move from time to time. If yours differ, check Anthropic’s help centre for custom connectors.
- STEP 01
claude.ai and Claude Desktop
Open Settings → Connectors and choose Add custom connector. Name it Defense Explorer and paste the server URL. Claude opens a Defense Explorer sign-in; approve the scopes you want.
Custom connectors depend on your Claude plan, and on Team or Enterprise workspaces an organisation owner may need to add or allow the connector first. Claude Desktop uses the same connectors as your claude.ai account.
Name: Defense Explorer URL: https://api.defenseexplorer.com/mcp - STEP 02
Claude Code
Add the server over HTTP transport, then run /mcp inside Claude Code, select defense-explorer and complete the browser sign-in.
claude mcp add --transport http defense-explorer https://api.defenseexplorer.com/mcp # then, inside Claude Code /mcp - STEP 03
Check the connection
Ask Claude “Which procurement sources can you see, and when were they last updated?”. It should call list_sources and report coverage, freshness and any open incident per source.
Tools Claude gets
[ CORE TOOLS ]The ten tools Claude reaches for most. The [full list of 24](/integrations/mcp/) is on the server page.
| Tool | Scope | What it returns |
|---|---|---|
| search_opportunities | mcp:read | Normalized, deduplicated notices filtered by query, source, type, country, CPV, value and dates, with official source links and English titles where translated |
| match_opportunities | mcp:read | Notices ranked against your company profile, each with its 0–100 score, reasons, unknowns and blockers |
| ask_opportunity | mcp:ai | A grounded answer about one notice, with sources and a document coverage note; facts are kept apart from inferences |
| get_brief | mcp:read | The cited brief: each claim with the document span it cites and the verbatim quote, plus a stale flag |
| get_document_coverage | mcp:read | Documents registered for a notice, their parse status and an explicit limitations list |
| list_pursuits / get_pursuit | mcp:read | The notices your team is working on, with stage, owner, next action and deadline |
| list_changes / get_change | mcp:read | Material amendments on followed notices, with original and updated clause text side by side |
| list_market_signals / get_market_signal | mcp:read | Early signals: prior information notices, market consultations, stated contract end dates, programme plans |
| list_sources | mcp:read | Every indexed source: coverage, freshness, counts, open incidents and known limitations |
| record_decision | mcp:write | Records a pursue, hold or decline decision a person has made, with their rationale, to the audit trail |
Things to ask Claude
[ 06 PROMPTS ]Claude chains tools on its own: search, then brief, then assessment.
- 01match_opportunities
“Which open NSPA tenders close in the next 30 days that fit our radio product line?”
Ranks open notices against the product line in your company profile and returns each score with its reasons, unknowns and blockers, so the assistant can say why a notice is on the list.
- 02get_brief · ask_opportunity
“Summarise the brief for this notice and tell me what the buyer wants as proof of past delivery.”
Every claim in the brief carries a page reference and a verbatim quote. Claims marked unknown or conflict come back labelled, not as facts.
- 03get_requirement_assessments
“Can we meet every mandatory requirement on the Dutch secure comms pursuit?”
Returns the qualification matrix. Only approved evidence inside its validity dates satisfies a requirement, and a blocked item names the rule that blocked it.
- 04list_changes · get_change
“What changed on the tenders we are following this week, and which requirements need a second look?”
Material amendments only, with the original and updated clause side by side. Cosmetic edits are excluded by default.
- 05summarize_market_signals
“What demand is building for counter-UAS in Germany and France over the next year?”
Counts prior information notices, market consultations and stated contract end dates by horizon. These are inferred demand, not open calls, and the assistant should say so.
- 06list_sources
“Do you cover Spanish Ministry of Defence tenders, and how fresh is that data?”
States what each source covers and leaves out, when it last succeeded and any open incident. This is the answer to “do you cover this?”, before anyone concludes a notice does not exist.
Working well with Claude
[ PRACTICE ]Put your capture context in a Claude Project: product lines, target buyers, clearances held. Claude then asks the server better questions, while the scores still come from the company profile in Defense Explorer, so they match what your colleagues see in the pipeline.
Ask Claude to quote the brief rather than paraphrase it when a claim will go into a bid/no-bid paper. Each claim links to a document span, and anything the source could not confirm comes back as unknown.
Spanish and French notices are stored in their original language. When searching PLACSP or BOAMP, ask Claude to search in Spanish or French as well as English.
Safety and permissions
[ WHAT IT WILL NOT DO ]An intelligence and workflow surface, not an autonomous procurement agent.
The server reads public procurement records and your workspace’s own data under the same company membership and permissions as the web app. Another workspace’s id returns “not found”, never “forbidden”, so ids cannot be probed. Access stops as soon as a membership ends or a token is revoked or expires.
Writes are deliberately narrow and all need mcp:write: saving or removing a watchlist item, recording a bid decision a person has already made, and acknowledging that an amendment was seen. An assistant cannot move a pursuit through stages on its own, approve evidence, edit a requirement or create an export.
It cannot submit bids, contact buyers, draft proposal text, access classified material, change billing or make arbitrary network requests. Raw source snapshots are never returned directly, because source pages and documents are untrusted input; ask_opportunity is the controlled path for reading indexed tender text.
Guard rails the tools make visible
A claim with status unknown or conflict is not a supported fact. Document coverage limitations matter: “no such clause” and “no such clause in the parts we could read” are different answers. Only an approved evidence item inside its validity dates can satisfy a requirement. Market signals are inferred demand, not open calls, and an estimated window is labelled as an estimate.
Coverage is defence-relevant, not complete national procurement, so list_sources should be checked before an assistant says a notice does not exist.
Other tender tools with MCP
[ HONEST CONTEXT ]MCP is becoming standard in this category. What differs is the data and the tools behind it.
Defense Explorer is not the only tender tool with an MCP connection. Tenderlake offers an MCP-based analyst for mainstream assistants, and Stotles added an MCP connector on its paid plans in August 2026. If you are comparing, see Defense Explorer vs Tenderlake and Defense Explorer vs Stotles.
What is specific here: notices classified for defence relevance and clearance evidence with the reason shown; NATO/NSPA and national European sources alongside TED; briefs that cite the page and quote the text; a qualification matrix tied to reviewed company evidence; amendment impact; and write tools limited to recording what a person decided.
Questions
[ 05 ANSWERS ]01Do I need a token to use Defense Explorer in Claude?
No. Claude supports MCP OAuth, so you add the URL and sign in. Tokens are for clients that only accept custom headers, such as a Cursor config file.
02Which Claude plans support custom connectors?
That is set by Anthropic and changes over time, and organisation admins can restrict connectors. Check Anthropic’s help centre for custom connectors for the current list.
03Can Claude record a bid decision for us?
Only if you grant mcp:write, and only a decision a person has made, with their rationale. The decision goes to the audit trail, supersedes the previous one without deleting it, and notes that it came in over MCP.
04Does Claude see other workspaces’ pursuits?
No. The connection is scoped to your active company membership. Another workspace’s id returns “not found”.
05How do I disconnect?
Remove the connector in Claude, or revoke the connection in Defense Explorer Integrations. Access also ends if your company membership ends.
Ask Claude which tenders are worth your time.
Start a Team trial, add the connector, and get cited answers in minutes.