MCP server
Bidderops exposes a Model Context Protocol (MCP) server so AI assistants — such as Claude or Cursor — can securely read and act on your bid pipeline on your behalf. Instead of copy-pasting between tools, you can ask your assistant questions like “what deadlines are coming up this week?” and have it answer from live Bidderops data.
How a connection works
The MCP endpoint is an authenticated connection bound to your account. At a high level:
- Your assistant connects to the Bidderops
/mcpendpoint. - Because it is unauthenticated, the server points the assistant at its authorization server (standard OAuth 2.1 discovery).
- The assistant registers itself and opens an authorization page where you log in.
- After you approve, the assistant receives a short-lived access token tied to your session.
- Every tool call the assistant makes runs as you, under the same data isolation that applies in the app — so it can only ever see your organization’s data, and only what your role permits.
Connecting an assistant
Settings → Integrations is the home for the MCP connection: it shows your organization’s copyable MCP URL, the list of tools your plan makes available, and every assistant currently connected under your account. Paste the URL into your assistant’s MCP or connector settings and complete the sign-in it opens.
You can review and revoke connected assistants at any time from the same page. Revoking a connection invalidates its tokens immediately; the assistant would have to go through the authorization flow again to reconnect.
Available tools
Read
| Tool | What it does |
|---|---|
list_opportunities | List opportunities, optionally filtered by status or text. |
get_opportunity | Fetch one opportunity with its notes, documents, milestones, team members, and outcome. |
upcoming_deadlines | List active opportunities with a submission deadline within the next N days (default 14). |
pipeline_summary | Headline metrics: count by status, open count, open pipeline value, and win rate. |
summarize_losses | Group lost bids by loss reason and collect lessons-learned notes. |
Write
| Tool | What it does |
|---|---|
add_note | Add a timestamped note to an opportunity. |
create_opportunity | Create a new opportunity in your pipeline. |
update_opportunity | Update fields on an existing opportunity. |
add_milestone / set_milestone_complete | Add a milestone, or mark one complete. |
record_outcome | Record a won/lost result and move the bid to that status. |
add_team_member | Assign an organization member to the bid team. |
add_document_link | Attach a document to an opportunity as a link. |
AI
These run your organization’s own AI bid tools and use the model you have configured for
each feature in Settings → AI. They are available when your plan includes AI bid
tools; capability_match also requires the Experience & expertise feature, and the
intelligence tools require the Bid intelligence agent feature.
| Tool | What it does |
|---|---|
go_no_go_advice | Generate a go/no-go recommendation with reasoning and factors. |
analyze_rfp | Extract scope, evaluation criteria, milestones, and key dates from RFP text. |
capability_match | Judge how credibly you can deliver an opportunity from your experience and personnel. |
pipeline_report | Produce a management briefing across the whole active pipeline. |
generate_bid_intelligence | Run the web-grounded intelligence agent for a deep dossier. |
get_bid_intelligence | Read the latest stored intelligence dossier for an opportunity. |
Search and Experience library
| Tool | What it does |
|---|---|
search_experience | Find company project references by sector, country, or keyword. |
search_personnel | Find experts by sector, country, or keyword, for staffing. |
create_business_reference | Add a company project reference, mapping a reference sheet or project document into structured fields. |
create_personnel | Add an expert profile (CV), including the person’s assignment history. |
search_sourced_opportunities | Browse the discovery inbox of externally-sourced tenders. |
import_sourced_opportunity | Import a sourced tender into your pipeline. |
The four experience tools require the Experience & expertise feature; the discovery tools require Opportunity discovery. When you ask your assistant to add a CV or reference from a file, it maps the document into each tool’s typed fields — so the data lands in the right columns without manual entry.
Reads are available to any role; writes (and AI tools that persist a report) require an editor role, and that boundary is enforced by the database — not just the tool — so a viewer’s assistant cannot write even if asked to. Tools are only offered when your plan includes the matching feature.
Resources
Assistants that support MCP resources can browse and @-mention your pipeline directly:
bidderist://opportunity/{id}— a single opportunity with its notes, documents, milestones, team, and outcome (the same data asget_opportunity).bidderist://pipeline/summary— your headline pipeline metrics.
Prompts
The server ships a few ready-made prompts you can pick in your assistant:
- Weekly deadline digest — summarize the bids due soon and what needs attention.
- Draft go/no-go — a go/no-go memo for one opportunity.
- Loss retrospective — patterns and lessons from lost bids.
- Bid kickoff brief — a one-page kickoff brief for a bid team.
Self-hosting the connector
A standalone MCP connector is also available to run yourself, either as a local
subprocess (stdio) or as a small hosted service with the same OAuth flow. It covers
the data tools (reads, writes, searches, and imports); the AI tools, resources, and
prompts are served only by the built-in /mcp endpoint. Most teams should simply
connect to the built-in endpoint — self-hosting is for environments with policies
that require the connector process to run inside your own network.