Research MCP
io.github.research-mcp-hqPublished by GitHub account research-mcp-hqv0.1.2Updated Oct 24, 2026
Cited research MCP (MCP+agent infra): brief, lookup. Fail=$0.
Overview
A paid remote MCP server that gives assistants cited research briefs and single-source lookups on AI infrastructure, MCP and security topics.
- What you can do
- Produce cited, query-tied excerpt packs on AI infra, MCP and security topics, at quick or standard depth, returning a summary, body, confidence, sources, gaps and an as-of date. Fetch and verify one URL or claim, returning the same envelope with claims and excerpts. Refuse a run when quotes fail verification against the source URL, in which case it is not billed. Check the prepaid credit balance and published price tables through the billing credits endpoint.
- When to use it
- Use it when an agent needs sourced, quotable research on AI infrastructure, MCP or security, or needs to verify a single URL or claim, and the user is willing to pay per successful call from a prepaid balance.
- Requirements
- Remote streamable HTTP endpoint; no local install. A bearer API key from prepaid checkout, sent in the Authorization header (an X-API-Key header is also accepted). Network access to the hosted endpoint. Credits must be purchased in advance.
Installation
In SourceWeft
- Open Research MCP in the dashboard and add it to a workspace.
- Connect Authorization token credentials. They are stored privately and never shown on public pages.
- Enable the server for the chats that should use its tools.
Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.
Use with an agent
Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.
Read https://sourceweft.com/mcp/io.github.research-mcp-hq%2Fresearch-mcp/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.Other MCP clients
Add this to your client's mcpServers config.
{
"mcpServers": {
"research": {
"type": "http",
"url": "https://mcp.researchmcp.dev/mcp",
"headers": {
"Authorization": "Bearer <YOUR_TOKEN>"
}
}
}
}README
research-mcp
Paid cited research remote MCP for coding / research agents (API key auth, not OAuth).
Why pay: query-tied excerpt packs from allowlisted primaries; refuse uncited — that call is $0. Prepaid packs; meters only on billable successes.
Repo may be private; treat this README as the agent-facing contract. Live Fly host is unchanged.
Marketing site (Cloudflare Pages)
Source of truth: research-mcp-hq/www (public/). Live site: https://researchmcp.dev.
The www/ tree in this repo is a stub / mirror note only — do not point Cloudflare Pages here. MCP API origin remains on Fly; branded install URL is https://mcp.researchmcp.dev/mcp.
MCP URL (production)
Health: https://mcp.researchmcp.dev/health
Server card: https://mcp.researchmcp.dev/.well-known/mcp/server-card.json
Credits meter: GET https://mcp.researchmcp.dev/billing/credits (auth’d)
Auth
Every /mcp and /billing/credits request:
Authorization: Bearer <key>orX-API-Key: <key>
Keys: prepaid customer key (from Checkout success page) or break-glass API_KEYS (ops; no ledger debit).
Privacy (demand signals)
We log category mix (tool, topic bucket, host, billable vs fail=$0) — not your questions. Opt-in via DEMAND_LOG=1 on the server; default off.
Pricing (locked)
fail = $0: sample/demo, quote-gate fail, density fail, COGS abort, cancel, depth-mismatched golden, preview/parked paths (meta.billable=false, charge_usd=0).
Inspect balance + tables: GET /billing/credits → balance_cents, packs, meters_usd, fail_usd: 0. Break-glass returns { break_glass: true, balance_cents: null } (no fake balance).
When to call each tool
Live (default paid surface)
Both return the shared envelope: tldr, body, confidence, sources, gaps, as_of, plus schema_version (2026-09-14). Optional fail_gate: { reason, retryable }, claims / excerpts, retrieved_at. If quotes fail verification on source_url, the run is refused and not billed.
Preview / parked (ENABLE_PREVIEW_TOOLS=1)
Without the flag: compare_options is not registered; depth=deep is rejected (preview_required). Directory card still says do-not-call for compare/deep.
No stub billing. No 25-tool kitchen sink — two live tools by default.
Published contract
- Schema:
docs/contract/schema.json - Examples:
docs/contract/examples/happy-research-brief.json,fail-gate.json - HTTP header on responses:
X-Research-MCP-Schema-Version: 2026-09-14 - Tool notes:
docs/TOOLS.md
Quickstart (local)
Env (high-signal)
Tests
Layout
src/server.ts— tool registration (finish-or-hide)src/billing/credits.ts—GET /billing/credits(T10 visible meter)src/contract.ts—schema_version+fail_gatedocs/contract/— published JSON Schema + examplesARCHITECTURE.md— transport / auth / metering
Discovery
Homepage for listings: https://researchmcp.dev, not Smithery.
Ops
See RUNBOOK.md. License: MIT.
Source: README.md at commit 15ce435
Tools
0Version history
1- v0.1.2LatestSep 16, 2026
Score
85% of the applicable checks met
How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.
- Reached in the last 30 daysRequired25 pts
- Auth declaredRequired10 pts
- Tools listed15 pts
Answer tools/list without a credential, or ship a package that starts in a sandbox without one.
- DescriptionRequired15 pts
- Logo10 pts
- Documentation15 pts
- License10 pts