INTEGRATION · Pro Max
Use BidSparq from any AI chat.
Connect Claude, Cursor, ChatGPT, or any MCP-compatible client. Your AI assistant gets instant access to 103 tools across 50,000+ active RFPs, 1.8M+ closed RFPs, 2M+ federal awards, 100,000+ subaward records, and 400,000+ SAM-registered vendors.
MCP server URL
https://bidsparq.com/mcpWorks with the MCP-compatible AI clients you already use
How it works
Ask in plain English. Get back real data.
Once connected, your AI client calls BidSparq tools the same way it calls its built-in ones. Here's what you can ask, and what comes back.
“What am I watching right now?”
list_saved_searches
Every saved search on the account with its keywords, NAICS prefixes, states, value range, radius and alert status, plus the sentence it was drafted from. Read-only; create_saved_search adds a new one.“Anything new from the buyers I follow?”
get_saved_signals
Saved pre-RFP signals, followed buyers with their 30-day signal counts, and the new signals at those buyers, each with the source document and the app link. get_my_signals returns the ranked feed for the whole profile.“What did DLA pay per unit for NSN 6135-01-210-8715?”
search_dla_awards
DIBBS award records and CLIN unit prices for that NIIN (the price DoD actually paid, with award numbers, dates and PDF links), plus FedMall order history with the buying agency. Works by NSN, manufacturer part number or company.“Which vendors sell janitorial supplies to Texas state agencies?”
search_purchase_lines
Vendors and buyers ranked by purchase-line count from the state and local purchase orders BidSparq holds, the states the lines come from, and unit prices per line, with FedMall orders and NASPO and Texas catalog prices alongside; never a spend total.“Who bid on the Nueces County bridge removal letting and at what price?”
search_bid_tabs
The TxDOT letting with every bidder, their rank and submitted bid total, the low bidder marked and the engineer's estimate, for lettings from August 2024 onward.“Find me primes who hire subs in NAICS 541512.”
find_subaward_primes
Top 20 primes ranked by subaward count, SAIC, GDIT, Peraton, Booz Allen, with sub_count, top awarding agencies, and example subawards. SAM-matched UEIs deduped across acquisitions (Perspecta + Peraton). Counts, not dollar totals: the subaward corpus is partial.“What's the typical award amount for VA software contracts?”
analyze_pricing_intel
p25 / median / p75 across the matching definitive awards BidSparq holds, plus the agency's median when you name one. Percentiles over a partial copy of USAspending, labelled as such.“Show me wired RFPs in defense IT so I know what to skip.”
filter_rfps (wired_only=true)
RFPs flagged by our wired-signal detector: brand-name lock-in, intent-to-award language, thin PWS, competitor-specific wording, with sourced excerpts.“What contracts come up for recompete in cybersecurity over the next 12 months?”
find_recompetes
Expiring contracts with the incumbent, days-until-expiry, contract value, and matching active RFPs by NAICS so you can see the new vehicle alongside the legacy one.“Tell me about NASA's buying patterns.”
get_agency_profile
Top NAICS codes and top vendors by award count, seasonal pattern (Q4 surge), median and max award size, and competition density. No spend totals: the awards corpus is partial. Sentinel/placeholder values filtered out.“Find HUBZone businesses in Texas for NAICS 541512.”
search_vendors
SAM-registered vendors with NAICS match + HUBZone certification active, including UEI, certifications, primary NAICS, location, and registration status.
Setup · under 2 minutes
Three steps and you're connected.
- 1
Upgrade to Pro Max
MCP access is included on the Pro Max plan: no separate fee and no per-call fee, within the published limits, shared with the in-app AI chat. See pricing →
- 2
Paste the URL in your AI client
Open your client's MCP settings, paste
https://bidsparq.com/mcp. Specific instructions per client below. - 3
Click “Allow” in your browser
Your AI client opens an OAuth consent page on BidSparq. Click Allow once: done. The connection auto-refreshes for 30 days. Revoke anytime at Settings → Integrations.
Setup in your AI client
Pick your client. Each has slightly different settings UI; the URL is the same.
Claude's built-in custom-connector screen handles the OAuth flow for you, with no JSON editing needed. The same steps work in Claude on the web.
- 1Open Claude and go to Customize → Connectors.
- 2Click + Add, then Add custom connector.
- 3Paste
https://bidsparq.com/mcpas the URL and click Add. Leave headers blank: Claude will start the OAuth dance automatically. - 4Click Connect. Your browser opens to BidSparq's consent page. Sign in if needed, then click Allow.
- 5Back in Claude Desktop, the BidSparq tools appear in the + menu of any chat. Try: “Find primes who hire subs in NAICS 541512”
On Claude Team and Enterprise plans an owner adds the connector once under Organization settings → Connectors. Each member then opens Customize → Connectors and clicks Connect.
Capabilities
All 103 tools, grouped by what you'd use them for.
RFP discovery
Find what to bid on next.
semantic_searchNatural-language topic search across 50,000+ active RFPs (pgvector HNSW + OpenAI embeddings).
filter_rfpsStructured filter: state, agency, NAICS prefix, set-aside, due dates, wired-only, keywords, sort by value.
count_rfpsAggregate counts grouped by state / agency / NAICS. Filters out scraper-placeholder agencies.
list_sourcesAll 130+ procurement sources we scrape with active RFP counts.
search_historical_bids1.8M+ closed RFPs with close-date sentinel cleanup, the deepest historical corpus in the market.
upcoming_deadlinesActive RFPs closing in the next N days (default 7). Filterable by NAICS / agency / state / set-aside-only. Sorted most-urgent first.
RFP analysis
Decide if an RFP is worth bidding.
get_rfp_detailsFull enrichment for one RFP: AI summary, win-fit, complexity, compliance items, wired signals, related awards.
get_compliance_matrixExtracted compliance requirements with section + page references straight from the PDF.
compare_rfpsSide-by-side comparison of 2-5 RFPs, value, NAICS, set-aside, AI win-probability, wired risk. Surfaces unresolved IDs.
search_rfp_documentsFull-text + semantic search inside attached PDFs scoped to one RFP.
Market intelligence
The BidSparq-only tools | built on our 1.8M+ historical RFPs, 2M+ awards, 100,000+ subawards, 400,000+ SAM entities.
find_subaward_primesPrimes who hired subs in your NAICS, 100,000+ FFATA records, 18-month window. UEI-deduped across acquisitions.
vendor_win_historyPer-vendor federal win history from 2M+ awards. By UEI or fuzzy name. Returns per-award detail + top agencies + cadence.
competitive_landscapeWin concentration by award count (top-1/3/10 share of the awards we hold), top vendors by count, avg bidders, set-aside mix, competition extent. The 'who am I really up against?' tool.
set_aside_analysisPer-set-aside breakdown for a NAICS: award counts, avg bidders, easier-than-baseline flag, top vendor per category. Use to evaluate certification ROI.
analyze_pricing_intelp25 / median / p75 POST-AWARD amounts over definitive awards (IDV ceilings excluded). Percentiles from the partial USAspending copy BidSparq holds, labelled as such.
budget_intelligencep25 / median / p75 PRE-RFP POSTED budget ranges from 1.8M+ historical RFPs. Planning $ vs. obligated $.
contract_duration_intelTypical contract length from 1.8M+ closed RFPs. Parses '1 year' / '36 months' / '5 years' patterns into months percentiles + buckets.
search_awardsPast contract awards by agency / NAICS / vendor. Filters $1T ceiling-amount sentinels.
find_recompetesExpiring contracts + incumbent + days-until-expiry + matching active RFPs (NAICS-locked).
get_agency_profileSpend stats, top vendors, top NAICS, max-award + competition density. VA → Veterans Affairs abbreviation routing.
get_seasonal_analysisMonthly award patterns by NAICS / agency, find when an agency actually buys.
get_trendingWeekly new-RFP counts grouped by state / source / bid type.
search_vendors400,000+ SAM-registered vendors with NAICS arrays, set-aside certs, UEI, location, expiration.
Personal relevance (signed-in only)
Uses BidSparq's 75K-row contractor×RFP scoring engine to answer 'what should I bid on?'
get_my_top_matchesYour highest-AI-scored active RFPs. Filterable by min_score, state, NAICS, decision verdict. Returns ai_score + llm_pwin + bid_recommendation per match.
explain_my_fitPer-RFP fit explanation: ai_score, Shipley Pwin, factor breakdown (capability/past-perf/set-aside/geography/complexity), compliance gaps, wired-risk.
find_similar_active_rfpsQuery-by-example: given an RFP id, find other ACTIVE RFPs whose scope reads like it. Uses pgvector HNSW embedding similarity, not just NAICS/agency filters.
get_pipelineYour bid pipeline (new_match → reviewing → preparing → submitted → won/lost) with notes.
Security & privacy
You stay in control of what your AI client can do.
OAuth 2.1 with PKCE
Connection uses OAuth 2.1: the same standard GitHub, Google, and your bank use. PKCE protects against code interception. No client secret to leak.
One limited scope (mcp:tools)
Your AI client gets a single scope: mcp:tools, to search your BidSparq data and manage your own pursuits (e.g. save an RFP, set a next action, advance a stage). It cannot change your account settings, billing, password, or any other connected app.
Conversation history stays in your client
BidSparq only sees the tool calls and their arguments (e.g., NAICS code, agency name). The wider conversation never leaves your AI client.
Revoke in one click
At Settings → Connected Apps you can see every client connected and disconnect any of them. All tokens for that client die immediately.
Tokens are hashed at rest
Access + refresh tokens are stored as sha256 hashes only. Even our database backups don't contain reversible credentials.
Auto-rotation, single-use refresh
Access tokens expire in 1 hour. Refresh tokens rotate on every use. Reuse of an old refresh token triggers a full revocation of the connection.
Alternative
Prefer static API keys for scripts and CI?
OAuth is the recommended path for everyday AI-client use. For scripted / headless / CI use cases, you can also use a long-lived Bearer key. Generate one at Settings → API Keys and paste it into the Authorization header of any of the configs below.
Remote URL (recommended for keys too)
{
"mcpServers": {
"bidsparq": {
"url": "https://bidsparq.com/mcp",
"headers": {
"Authorization": "Bearer bsq_live_..."
}
}
}
}npm package (for clients without remote-MCP support)
{
"mcpServers": {
"bidsparq": {
"command": "npx",
"args": ["-y", "bidsparq-mcp-server"],
"env": {
"BIDSPARQ_API_KEY": "bsq_live_..."
}
}
}
}Frequently asked
- Is the MCP integration free?
- Included with the Pro Max plan ($249/mo or $199 on annual). No additional usage fees and no per-call fee, within the published limits in the next answer, whether you use the in-app chat or your own MCP client. The rate-limit answer below gives the exact numbers.
- What's the rate limit?
- Per account, shared with the in-app AI chat: up to 60 tool calls a minute (refilling one a second), 500 an hour, and 5 running at once. No per-call fee. Automated access pauses at 2,000 AI and API calls in a day or 750 tool calls in an hour, with an email first at 1,000 a day: the pause is for bulk pulls, and support@bidsparq.com restores access for your own organization's business under the Terms (section 7). If you regularly need more, email support@bidsparq.com first.
- Can I use this for production / automation?
- Yes. Create a static API key at Settings → API Keys (bidsparq.com/settings/api-keys) and use it rather than OAuth for headless / CI workloads. Apps connected through OAuth are listed, and can be disconnected, at Settings → Integrations. The same tools, same rate limits, same data.
- What happens if I downgrade from Pro Max?
- Your existing OAuth connections immediately stop working: the /mcp endpoint enforces tier on every call. Upgrade back and they resume.
- What if my AI client uses the wrong tool?
- Be specific in your prompt: e.g., 'use find_subaward_primes' instead of 'find me partners'. The tool descriptions are tuned for Claude 3.5+ and GPT-4-class models; smaller models may need more guidance.
- Can my organization audit what's been accessed?
- Yes. Every tool call is logged with timestamp, tool name, and arguments. Email support@bidsparq.com for an audit export.
- Do you sell or share my queries?
- No. Tool-call arguments stay on BidSparq's servers (US-based) and are only used to serve your request and for our internal abuse-prevention logs. We never sell or share your usage with third parties.
- What if the MCP server is down?
- Your AI client gets a clear error message and can fall back to its own knowledge. Our uptime target is 99.9%: track real-time at bidsparq.com/status (coming soon).
Troubleshooting
Tools missing in Claude Desktop / Cursor after install
Fully quit and relaunch the app: MCP servers are only loaded at startup. In Claude Desktop, click the + icon in the prompt area; bidsparq should appear in the tools list.
401 Unauthorized: Invalid or missing credentials
If using OAuth: your token may have expired or been revoked. Re-run the connection from your AI client. If using a Bearer key: the key may have been revoked, rolled, or reached its expiry date. Create a new one at Settings → API Keys.
403 Forbidden: Pro Max plan required
Your account is on Free or Pro. Upgrade at /plan. MCP access flips on within seconds of upgrade.
Rate limit: 60 requests/minute (or Hourly limit: 500 requests/hour)
Your client sent calls faster than the shared per-account limits (60 a minute, 500 an hour, 5 running at once). The error says how many seconds to wait; retry after that. A script that loops on a tool should pause between calls. If you're regularly hitting it, contact us.
`fetch failed` on first npx run
The npx command needs network access to fetch the package and call BidSparq's API. Make sure your firewall doesn't block outbound HTTPS to bidsparq.com and registry.npmjs.org.
Tool returns nothing for a specific NAICS
Try a prefix instead of an exact code: e.g., '5415' instead of '541512'. Some scrapers tag RFPs with broader categories. The naics field on most tools accepts both.
Ready to put your AI assistant to work?
Pro Max plan, then paste https://bidsparq.com/mcp into your AI client. Click Allow. Done.
Questions? support@bidsparq.com