Paid deep research-as-a-service MCP (MVP)
- ✓Open-source license (MIT)
- ✓Actively maintained (<30d)
- ✓Clear description
- ✓Documented (README)
git clone https://github.com/research-mcp-hq/research-mcp my-project && cd my-projectResumen de Templates
# 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)
Static landing for **https://researchmcp.dev** lives in [`www/`](./www/) (no build). Point Cloudflare Pages **root directory** at `/www`. MCP API remains on Fly — see `deploy/CLOUDFLARE_PAGES.md`.
## MCP URL (production)
```
https://mcp.researchmcp.dev/mcp
```
Health: `https://research-mcp-mhh.fly.dev/health`
Server card: `https://research-mcp-mhh.fly.dev/.well-known/mcp/server-card.json`
Credits meter: `GET https://research-mcp-mhh.fly.dev/billing/credits` (auth’d)
```json
{
"mcpServers": {
"research-mcp": {
"url": "https://mcp.researchmcp.dev/mcp",
"headers": {
"Authorization": "Bearer YOUR_API_KEY"
}
}
}
}
```
## Auth
Every `/mcp` and `/billing/credits` request:
- `Authorization: Bearer <key>` **or**
- `X-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)
| Pack | Credits |
| --- | --- |
| **$10** starter | 1000¢ |
| **$25** standard | 2500¢ |
| **$50** pro | 5000¢ |
| Meter (billable success) | Price |
| --- | --- |
| lite (`source_lookup`, `research_brief` depth=quick) | **$0.25** |
| standard (`research_brief` depth=standard) | **$0.60** |
| deep (preview only) | **$1.50** published meter; preview path always **$0** |
**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)
| Tool | Call when | Do not |
| --- | --- | --- |
| **`research_brief`** | You need cited, query-tied excerpt packs on AI infra / MCP / security. `depth=quick` ($0.25) or `depth=standard` ($0.60). | Do not use `depth=deep` (parked / sample only unless preview flag). |
| **`source_lookup`** | You have **one** URL or claim to fetch/verify. Lite $0.25. | Do not use as open-web search or multi-source synthesis. |
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`)
| Tool / path | Behavior |
| --- | --- |
| **`compare_options`** | Registered only with the flag. **Always $0** / `billable=false`. No live path — prefer `research_brief`. |
| **`depth=deep`** | Allowed only with the flag. **Always $0**. Soft-reserve never demands full deep SKU. |
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`](./docs/contract/schema.json)
- Examples: [`docs/contract/examples/happy-research-brief.json`](./docs/contract/examples/happy-research-brief.json), [`fail-gate.json`](./docs/contract/examples/fail-gate.json)
- HTTP header on responses: `X-Research-MCP-Schema-Version: 2026-09-14`
- Tool notes: [`docs/TOOLS.md`](./docs/TOOLS.md)
## Quickstart (local)
```bash
cd /workspace/research-mcp
npm install && npm run build
API_KEYS=dev-key-1 npm start
# optional live brief path:
LIVE_RESEARCH=1 API_KEYS=dev-key-1 npm start
```
```bash
curl -s http://127.0.0.1:3000/health
curl -s -X POST http://127.0.0.1:3000/mcp \
-H 'Content-Type: application/json' \
-H 'Accept: application/json, text/event-stream' \
-H 'Authorization: Bearer dev-key-1' \
-d '{"jsonrpc":"2.0","id":1,"method":"tools/list"}'
```
## Env (high-signal)
| Var | Notes |
| --- | --- |
| `API_KEYS` | Break-glass keys (comma-separated) |
| `LIVE_RESEARCH=1` | Live search→extract→synthesize→quote gate for quick/standard |
| `ENABLE_PREVIEW_TOOLS=1` | Register compare + allow deep (always $0) |
| `DATABASE_URL` | SQLite ledger for customer keys / credits |
| Stripe `STRIPE_*` / pack price IDs | Prepaid Checkout (test until go-live) |
## Tests
```bash
npm run eval:all # goldens + off-golden + pipeline
npm run test:billing # ledger / webhook / credits meter
```
## 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_gate`
- `docs/contract/` — published JSON Schema + examples
- `ARCHITECTURE.md` — transport / auth / metering
## Discovery
| Surface | URL / ID |
| --- | --- |
| GitHub | https://github.com/research-mcp-hq/research-mcp |
| Fly MCP | https://mcp.researchmcp.dev/mcp |
| Smithery (discovery only) | https://smithery.ai/servers/research-mcp-hq/research-mcp |
Homepage for listings: **https://researchmcp.dev**, not Smithery.
## Ops
See [RUNBOOK.md](./RUNBOOK.md). License: [MIT](./LICENSE).
Lo que la gente pregunta sobre research-mcp
¿Qué es research-mcp-hq/research-mcp?
+
research-mcp-hq/research-mcp es templates para el ecosistema de Claude AI. Paid deep research-as-a-service MCP (MVP) Tiene 0 estrellas en GitHub y su última actualización registrada es del 2026-09-14.
¿Cómo se instala research-mcp?
+
Puedes instalar research-mcp clonando el repositorio (https://github.com/research-mcp-hq/research-mcp) o siguiendo las instrucciones del README en GitHub. ClaudeWave también te ofrece bloques de instalación rápida en esta misma página.
¿Es seguro usar research-mcp-hq/research-mcp?
+
Nuestro agente de seguridad ha analizado research-mcp-hq/research-mcp y le ha asignado un Trust Score de 87/100 (tier: Trusted). Revisa el desglose completo de comprobaciones superadas y flags en esta página.
¿Quién mantiene research-mcp-hq/research-mcp?
+
research-mcp-hq/research-mcp es mantenido por research-mcp-hq. La última actividad registrada en GitHub es del 2026-09-14, con 1 issues abiertos.
¿Hay alternativas a research-mcp?
+
Sí. En ClaudeWave puedes explorar templates similares en /categories/templates, ordenados por popularidad o actividad reciente.
Despliega research-mcp en tu cloud
Lleva este repo a producción en minutos. Cada plataforma genera su propio entorno con variables de entorno editables.
¿Mantienes este repo? Añade un badge a tu README
Pega el badge en tu README de GitHub para mostrar que está auditado por ClaudeWave. Cada badge enlaza de vuelta a esta página y muestra el Trust Score actual.
[](https://claudewave.com/repo/research-mcp-hq-research-mcp)<a href="https://claudewave.com/repo/research-mcp-hq-research-mcp"><img src="https://claudewave.com/api/badge/research-mcp-hq-research-mcp" alt="Featured on ClaudeWave: research-mcp-hq/research-mcp" width="320" height="64" /></a>Más Templates
CLI tool for configuring and monitoring Claude Code
AWS AI Stack – A ready-to-use, full-stack boilerplate project for building serverless AI applications on AWS
Scaffold production-ready full-stack apps in TypeScript, Rust, Python, Go, and Java with a visual builder and CLI. Choose your frontend, backend, database, auth, AI, payments, and DevOps integrations, all wired together.
From Claude Artifact to deployable React app — in seconds!
CLAUDE.md best practices
No description provided.