Conecta clientes de IA con Zearch para realizar investigaciones con respuestas verificadas mediante fuentes citadas y fragmentos exactos.
También conocido como zearchcomputer/zearch-mcp, zearch-mcp, @zearchcomputer/mcp
- Stars
- 0
- Herramientas
- 6
- Descargas, 30 días
- —
- Última versión
- 0.1.0
- Último commit
- 3 nov 2026
- Licencia
- MIT
¿Qué es Zearch MCP?
Conecta clientes de IA con Zearch para realizar investigaciones con respuestas verificadas mediante fuentes citadas y fragmentos exactos. Expone 6 herramientas, como research, verify, get_run.
Resumen generado a partir del README del proyecto
Acerca del MCP server de Zearch
Zearch te permite realizar investigaciones con citas verificadas directamente desde tu entorno de desarrollo de IA. Conecta clientes de Model Context Protocol como Claude, Cursor y VS Code con el motor de Zearch para proporcionar respuestas donde cada párrafo se comprueba contra fragmentos específicos de las fuentes. Esto asegura que la información proporcionada esté basada en evidencia en lugar de alucinaciones del modelo.
Los desarrolladores utilizan esta herramienta de investigación para realizar búsquedas estándar, informes profundos basados en hasta ocho fuentes o rastreo de sitios (site crawling). El servidor también incluye una herramienta de verificación para contrastar tus propios textos con las fuentes proporcionadas, otorgando puntuaciones de aprobación o fallo y atribuciones. Los usuarios también pueden realizar investigación inversa para entender cómo funciona una aplicación o repositorio mediante análisis estático.
La configuración requiere una clave de API de Zearch y puede ejecutarse localmente vía npx o en modo HTTP remoto. El servidor admite diferentes modos como scrape, compare y deep research, con costos gestionados mediante un sistema de créditos. Para los clientes que admiten MCP Apps, el servidor renderiza tarjetas interactivas que contienen chips de citación y extractos de las fuentes.
Qué puedes hacer con él
- 1Realizar informes de investigación profundaPide a la IA que genere un informe detallado basado en múltiples fuentes web con citas verificadas.
- 2Verificar la precisión de contenido escritoComprueba un borrador que hayas escrito contra un conjunto de fuentes para asegurar que cada afirmación esté respaldada.
- 3Analizar arquitectura de softwareUtiliza el análisis estático para entender el funcionamiento interno de un repositorio o aplicación específica.
- 4Extraer información de páginas web específicasExtrae y resume información de una sola página web directamente desde tu interfaz de chat.
Escrito a partir del README del proyecto. Cada caso de uso se verifica con una cita del mismo.
Cómo instalar Zearch MCP
Formatos verificados el 10 nov 2026Añadir a CursorAñadir a GooseInstalar Zearch MCP en Claude Code
$ claude mcp add --env 'ZEARCH_API_KEY=<YOUR_ZEARCH_API_KEY>' zearch-mcp -- npx -y @zearchcomputer/mcpInstalar Zearch MCP en Cursor
~/.cursor/mcp.json
{
"mcpServers": {
"zearch-mcp": {
"command": "npx",
"args": [
"-y",
"@zearchcomputer/mcp"
],
"env": {
"ZEARCH_API_KEY": "<YOUR_ZEARCH_API_KEY>"
}
}
}
}Instalar Zearch MCP en VS Code
.vscode/mcp.json
{
"servers": {
"zearch-mcp": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@zearchcomputer/mcp"
],
"env": {
"ZEARCH_API_KEY": "<YOUR_ZEARCH_API_KEY>"
}
}
}
}Instalar Zearch MCP en VS Code CLI
$ code --add-mcp '{"name":"zearch-mcp","type":"stdio","command":"npx","args":["-y","@zearchcomputer/mcp"],"env":{"ZEARCH_API_KEY":"<YOUR_ZEARCH_API_KEY>"}}'Instalar Zearch MCP en Claude Desktop
claude_desktop_config.json
{
"mcpServers": {
"zearch-mcp": {
"command": "npx",
"args": [
"-y",
"@zearchcomputer/mcp"
],
"env": {
"ZEARCH_API_KEY": "<YOUR_ZEARCH_API_KEY>"
}
}
}
}Instalar Zearch MCP en Codex
$ codex mcp add zearch-mcp --env 'ZEARCH_API_KEY=<YOUR_ZEARCH_API_KEY>' -- npx -y @zearchcomputer/mcpInstalar Zearch MCP en Codex config.toml
~/.codex/config.toml
[mcp_servers.zearch-mcp] command = "npx" args = ["-y", "@zearchcomputer/mcp"] [mcp_servers.zearch-mcp.env] ZEARCH_API_KEY = "<YOUR_ZEARCH_API_KEY>"
Instalar Zearch MCP en Gemini CLI
$ gemini mcp add -s user -e 'ZEARCH_API_KEY=<YOUR_ZEARCH_API_KEY>' zearch-mcp npx -- -y @zearchcomputer/mcpInstalar Zearch MCP en Gemini settings.json
~/.gemini/settings.json
{
"mcpServers": {
"zearch-mcp": {
"command": "npx",
"args": [
"-y",
"@zearchcomputer/mcp"
],
"env": {
"ZEARCH_API_KEY": "<YOUR_ZEARCH_API_KEY>"
}
}
}
}Herramientas de Zearch MCP 6
Detectado desde el READMEresearchverifyget_runlist_runsget_walletget_pricing
| research | — | |
| verify | — | |
| get_run | — | |
| list_runs | — | |
| get_wallet | — | |
| get_pricing | — |
Configuración
ZEARCH_API_KEYObligatorioSecretoZearch API key (zk_live_…), from Account → API keys
ZEARCH_API_URLAPI base URL; defaults to https://zearch.computer/v1
| Nombre | Descripción | Tipo |
|---|---|---|
| ZEARCH_API_KEY | Zearch API key (zk_live_…), from Account → API keys | ObligatorioSecreto |
| ZEARCH_API_URL | API base URL; defaults to https://zearch.computer/v1 |
Verificaciones automáticas
Ejecutado 13 nov 2026Informe completo →Pasó nuestras verificaciones automáticas. Esto no es una auditoría de seguridad: lee el código y dale al servidor el acceso más limitado que necesite. Cómo funcionan las verificaciones
- Repositorio de origen vinculado y accesiblezearchcomputer/zearch-mcp is public and reachablegithub.com/zearchcomputer/zearch-mcp ↗Aprobado
- El paquete indica este repositorio como su origen@zearchcomputer/mcp names zearchcomputer/zearch-mcp as sourcenpmjs.com/package/@zearchcomputer/mcp ↗Aprobado
- Procedencia de la compilación (atestación de Sigstore)Sigstore attestation for @zearchcomputer/mcpnpmjs.com/package/@zearchcomputer/mcp/v/0.1.0#provenance ↗Aprobado
- Licencia de código abierto (OSI)MITspdx.org/licenses/MIT.html ↗Aprobado
- Commit o lanzamiento en el último añoLast commit or release 2026-11-03github.com/zearchcomputer/zearch-mcp ↗Aprobado
- OpenSSF ScorecardNo verificado
- El nombre del paquete no es similar a un paquete popularNo popular package one edit away from @zearchcomputer/mcpAprobado
- No hay avisos críticos en el paquete ni en sus dependencias4 resolved dependencies checked; no critical advisoryosv.dev ↗Aprobado
- Sin instrucciones ocultas para el modelo6 tool descriptions and the README read; no override phrases, credential paths or hidden charactersAprobado
- Las herramientas destructivas están etiquetadasNo tool named like delete, drop or execAprobado
- El endpoint remoto responde al handshake de MCPNo verificado
README
Ver en GitHub@zearchcomputer/mcp connects Claude, Cursor, VS Code and other Model Context Protocol clients to Zearch. Ask a question and you get an answer whose every paragraph was checked against the source it cites, with the exact passage Zearch read. Or check text your own model wrote against sources you already have.
Status: early. The Zearch API is not open to everyone yet.
How an answer is made
flowchart LR
Q([Question]) --> S[Search]
S --> J1[Jev selects<br/>passages]
J1 --> W[Writer drafts from<br/>those passages only]
W --> J2[Jev checks<br/>each paragraph]
J2 -->|supported| A([Cited answer])
J2 -->|not supported| E([The source<br/>passage itself])
Jev is TypeSafe AI's evidence model. When a paragraph can't be supported it is cut, and when nothing survives you get the best source passage instead of a guess (answer_type: "excerpt").
Tools
| Tool | What it does | Credits |
|---|---|---|
research |
Checked answer with numbered sources and the passages Jev read. Modes: standard, deep (a report from up to 8 sources), compare, scrape (one page), crawl (up to five pages of a site), reverse (how an app, repo or site works, from static analysis). Follow-ups with parent_id. |
1 · 5 · 2 · 1 · 3 · 10; follow-up 0.3 |
verify |
Checks your text against your sources, paragraph by paragraph: pass/fail, support and attribution scores. Cite sources as [1], [2]… |
1 |
get_run |
Reopens a run, or checks on a queued reverse run. |
free |
list_runs |
Your recent runs (shared with the Zearch app). | free |
get_wallet |
Credit balance, lots and expiry, recent ledger entries. | free |
get_pricing |
Public price list. No key needed. | free |
Errors are never charged. A run that can only return a source passage costs half.
Progress. research streams its stages (Searching the web → Choosing the most relevant evidence → Checking each claim against its source) as MCP progress notifications, so clients that show progress show what Zearch is doing.
Answer view. In clients that support MCP Apps, research, get_run and verify render an inline card: the answer with citation chips, source cards with the excerpt Jev read, an Open button for each source, and follow-up suggestions. It follows the client's light or dark theme. Other clients get the same content as text. Set ZEARCH_UI=0 to turn it off.
Resources. zearch://runs/{id} (a run as Markdown; your recent runs are listed), zearch://pricing.
Prompts. research_brief (a cited brief from deep research), fact_check (find sources for a draft, then verify it), compare (a table with a citation in every cell).
Install
You need a Zearch API key (zk_live_…). Create one in the Zearch app under Account → API keys.
Claude Code
claude mcp add zearch --env ZEARCH_API_KEY=zk_live_your_key -- npx -y @zearchcomputer/mcp
Claude Desktop
In Settings → Developer → Edit config, add:
{
"mcpServers": {
"zearch": {
"command": "npx",
"args": ["-y", "@zearchcomputer/mcp"],
"env": { "ZEARCH_API_KEY": "zk_live_your_key" }
}
}
}
Cursor
.cursor/mcp.json (project) or ~/.cursor/mcp.json (global): the same mcpServers block as Claude Desktop.
VS Code
.vscode/mcp.json, which prompts for the key instead of storing it:
{
"inputs": [{ "type": "promptString", "id": "zearch-key", "description": "Zearch API key", "password": true }],
"servers": {
"zearch": {
"type": "stdio",
"command": "npx",
"args": ["-y", "@zearchcomputer/mcp"],
"env": { "ZEARCH_API_KEY": "${input:zearch-key}" }
}
}
}
Run from source
git clone https://github.com/zearchcomputer/zearch-mcp
cd zearch-mcp
npm ci && npm run build
Then use node /absolute/path/to/zearch-mcp/dist/index.js as the command in any config above, instead of npx -y @zearchcomputer/mcp.
Remote (HTTP) mode
npx -y @zearchcomputer/mcp --http --port 8787 # http://127.0.0.1:8787/mcp
Every request uses the caller's own key, sent as Authorization: Bearer zk_live_…; the server stores no keys. ZEARCH_API_KEY is used as a fallback only when the server listens on loopback, so a public deployment can't spend the operator's credits for someone else. GET /healthz reports liveness.
To serve on a public interface, bind it and list the hostnames you serve, so requests with other Host headers are refused:
npx -y @zearchcomputer/mcp --http --host 0.0.0.0 --port 8080 --allowed-hosts mcp.zearch.computer
A Dockerfile is included for this.
Configuration
| Variable | Default | Purpose |
|---|---|---|
ZEARCH_API_KEY |
Your API key. In HTTP mode, callers send their own. | |
ZEARCH_API_URL |
https://zearch.computer/v1 |
API base URL. http:// is accepted only for localhost. |
ZEARCH_TIMEOUT_MS |
120000 |
Per-request timeout. Research streams get at least 180 s. |
ZEARCH_REVERSE_WAIT_MS |
300000 |
How long research waits for a reverse run before returning its id for get_run. |
ZEARCH_UI |
on | 0 turns off the inline answer view. |
ZEARCH_MCP_ALLOWED_HOSTS |
Same as --allowed-hosts. |
|
PORT |
8787 |
HTTP port when --port isn't given. |
Reliability
- Each
researchcall carries an idempotency key, reused across retries, so a retried request never runs or charges twice. - Network failures, 5xx responses and per-minute rate limits are retried with backoff that honours
Retry-After. Out-of-credit, auth and validation errors are not retried; they come back as a tool error that says what to do next. - If a research stream drops, the server reads the finished run instead of failing.
- Cancelling a tool call in the client cancels the request to Zearch.
- Logs go to stderr. Keys are never logged.
Development
npm ci
npm test # builds, then runs the tests against a local mock of the Zearch API
Tests make no network calls beyond localhost and spend no credits. The view is a single dependency-free HTML file in src/ui/answer.html.
The server is built on the MCP TypeScript SDK v2 (protocol revision 2026-07-28, with 2025-era clients still served) and talks to the Zearch API.
Security
Report vulnerabilities privately through GitHub security advisories. See the security policy.
License
Preguntas sobre Zearch MCP
¿Cómo agrego Zearch MCP a Claude Code?
Ejecuta claude mcp add --env 'ZEARCH_API_KEY=<YOUR_ZEARCH_API_KEY>' zearch-mcp -- npx -y @zearchcomputer/mcp en tu terminal. Añade --scope user para que esté disponible en todos los proyectos.
¿Cómo agrego Zearch MCP a Cursor?
Abre ~/.cursor/mcp.json y añade el servidor en mcpServers, usando la configuración de Cursor que se muestra en la sección de instalación de arriba.
¿Qué herramientas proporciona Zearch MCP?
Expone 6 herramientas, incluidas research, verify, get_run, list_runs, get_wallet.
¿Cómo garantiza Zearch que las respuestas sean precisas?
Cada párrafo de una respuesta se verifica con la fuente que cita; si un párrafo no puede ser respaldado, se elimina o se reemplaza con el fragmento de la fuente.
¿El servidor cobra por los errores?
No, los errores nunca se cobran, y las ejecuciones que solo pueden devolver un fragmento de la fuente cuestan la mitad del precio.