TokenSafe
Reduce your AI bills by up to 99% locally: focused code, warm prompt caches & zero secret leaks.
Servidor MCP · de tokensafe.dev
Resumen
TokenSafe es un servidor MCP publicado por tokensafe.dev. Marketplaces que leemos y que lo publican: 1 (Official MCP Registry). El último cambio que registramos fue el 2026-11-15. Según nuestra pasada por los marketplaces del 2026-11-15.
Qué pide
- Se ejecuta en remoto
Ninguno de los marketplaces que leemos publica sus herramientas ni los ajustes que pide.
Requiere: cabecera Authorization
Lo que declara, pide y ejecuta, completo
Instala solo plugins de desarrolladores en los que confíes. Mostramos lo que publican los marketplaces y no probamos plugins.
Funciona con
- Claude Code
- Codex
- Cursor
- VS Code
- Copilot CLI
Un enlace de un clic abre el cliente, que pide confirmación antes de añadir el servidor.
Según los marketplaces que lo listan y el transporte MCP que declara, tal como lo documenta cada cliente. No probamos plugins.
Conectar
Comandos y configuraciones generados solo a partir de lo que declaran sus marketplaces. No los ejecutamos por ti ni probamos plugins.
Como servidor MCP remoto
Generado a partir de lo que declara Official MCP Registry.
claude mcp add --transport http tokensafe https://api.tokensafe.dev/mcp --header "Authorization: Bearer <YOUR_TOKENSAFE_LICENSE_KEY>"[mcp_servers.tokensafe]
url = "https://api.tokensafe.dev/mcp"
http_headers = { "Authorization" = "Bearer <YOUR_TOKENSAFE_LICENSE_KEY>" }{
"mcpServers": {
"tokensafe": {
"url": "https://api.tokensafe.dev/mcp",
"headers": {
"Authorization": "Bearer <YOUR_TOKENSAFE_LICENSE_KEY>"
}
}
}
}Sustituya los valores entre corchetes angulares por los suyos. Mostramos los nombres de los ajustes, nunca valores.
Dónde está publicado
| Marketplace | Estado | Versión | Cifras | Verificado | Visto por primera vez |
|---|---|---|---|---|---|
| Official MCP Registry (Abrir el registro) | Publicado | 3.2.0 | Forks (GitHub): 2 Estrellas (GitHub): 41 |
Sin marca |
Cada cifra es del propio marketplace y nunca se suma entre marketplaces. Un marketplace que no publica cifras no muestra ninguna: sin número no es cero.
Cómo han cambiado sus cifras
- 2026-11-132
- 2026-11-142
- 2026-11-112
- 2026-11-1338
- 2026-11-1441
Cada punto es un día en que leímos un número distinto; los tramos planos son días en que el número no cambió. Las cifras de distintos marketplaces nunca se suman.
Qué cambió
- Official MCP Registry: publicó la versión 3.2.0 (antes 3.1.5)
- Official MCP Registry: publicó la versión 3.1.5 (antes 3.1.4)
- Official MCP Registry: publicó la versión 3.1.4 (antes 3.1.3)
- Official MCP Registry: publicó la versión 3.1.3 (antes 3.1.2)
- Official MCP Registry: publicó la versión 3.1.2 (antes 3.1.1)
- Official MCP Registry: publicó la versión 3.1.1 (antes 3.1.0)
- Official MCP Registry: publicó la versión 3.1.0 (antes 3.0.1)
- Official MCP Registry: publicó la versión 3.0.1 (antes 3.0.0)
- Official MCP Registry: publicó la versión 3.0.0 (antes 2.9.0)
- Official MCP Registry: publicó la versión 2.9.0 (antes 2.8.3)
- Official MCP Registry: publicó la versión 2.8.3 (antes 2.8.1)
- Official MCP Registry: publicó la versión 2.8.1 (antes 2.8.0)
- Official MCP Registry: publicó la versión 2.8.0 (antes 2.7.3)
- Official MCP Registry: publicó la versión 2.7.3 (antes 2.7.1)
- Official MCP Registry: publicó la versión 2.7.1 (antes 2.7.0)
- Official MCP Registry: publicó la versión 2.7.0 (antes 2.6.1)
- Official MCP Registry: publicó la versión 2.6.1 (antes 2.6.0)
- Official MCP Registry: publicó la versión 2.6.0 (antes 2.5.2)
- Official MCP Registry: cambió la descripción
- Official MCP Registry: publicó la versión 2.5.2 (antes 2.5.0)
Se muestran las últimas 20 de 37 entradas. El historial completo está en la app.
Plugins similares
Productos cuyos propios nombres, descripciones, herramientas y skills son los más cercanos a este por su significado, en todos los marketplaces que leemos. La cercanía se ordena solo dentro de esta lista.
-
Secure MCP server framework with 23 security layers and ML threat detection. Zero deps.
-
Local secret & credential checks for AI-assisted dev — runs on your machine, results redacted.
-
guardrails io.github.ExpertVagabond/guardrails
AI Agent Guardrails MCP server - security layer
-
secureflows-mcp io.github.michal-lefler/secureflows-mcp
MCP server for secureFlows: token-free URL builders and integration-linting tools for AI agents.
-
Sniff out what your AI tools are hiding: local security checks for MCP servers (hidden instructions, known malware, leaked secrets, rug pulls).
-
ai-agent-firewall com.fidacy/ai-agent-firewall
Every agent action watched, every money-moving one gated, every verdict independently verifiable.
-
security-proxy io.github.4hmetuyar/security-proxy
MCP gateway: many servers, one policy, lethal-trifecta blocking, PII masking, audit log
-
agent-security-scanner-mcp io.github.sinewaveai/agent-security-scanner-mcp
Security layer for AI agents: blocks prompt injection, detects fake packages, scans vulnerabilities.
-
Protect your AI agents and IDEs from malicious open-source packages.
-
inkog io.github.inkog-io/inkog
Security co-pilot for AI agents. Scan for vulnerabilities, audit MCP servers, verify governance.
Plugins similares por marketplace
La misma pregunta a cada marketplace por separado: ¿hay allí un equivalente de este plugin?
Publicado en Claude Code: claude-plugins-community (5)
-
Secure MCP servers with OAuth 2.1, token introspection, dynamic client registration, and CIMD so AI agents can call your MCP tools with verified identities
-
Real-time security filter for MCP tool communications. Works as a Claude Code hook to inspect all data sent to and received from MCP servers. Detects prompt injection, API key…
-
MCP security gateway that wraps any MCP server with per-tool policies, Ed25519-signed decision receipts, and human approval gates. Shadow mode (default) logs every tool call…
-
Convert MCP servers to token-efficient CLI tools with auto-generated SKILL.md files for Claude Code agents
-
agent-discover io.github.keshrath/agent-discover
Find, install and enable MCP servers mid-session on any host, with consent and tool pinning
Publicado en Claude Code: claude-plugins-official (5)
-
Set up endorctl and use Endor Labs to scan, prioritize, and fix security risks across your software supply chain
-
Connect Claude to a private MCP server through an Anthropic MCP tunnel. The /create-docker-mcp-tunnel command drives the Docker Compose quickstart end to end: certificates, proxy…
-
mcp-server io.github.cap-js/mcp-server
Model Context Protocol (MCP) server for AI-assisted development of CAP applications.
-
Detect an MCP server's language (Python, TypeScript or Go) and instrument it with the matching Pendo SDK so MCP tool calls flow into Pendo Agent Analytics.
-
Skills for creating MCP Apps with the MCP Apps SDK
Publicado en Claude: knowledge-work-plugins (5)
-
Hosted MCP server for AI-assisted Grafana Cloud observability — no local installation required.
-
The Vanta plugin connects Claude Code to Vanta's security and compliance platform through the Vanta MCP server. It combines Vanta's test-specific remediation intelligence with…
-
Sanity content platform integration with MCP server, agent skills, and slash commands. Query and author content, build and optimize GROQ queries, design schemas, and set up Visual…
-
MCP server for terminal commands, file operations, and process management
-
Figma design platform integration. Access design files, extract component information, read design tokens, and translate designs into code. Bridge the gap between design and…
Publicado en Codex: openai-curated (openai/plugins) (5)
-
Cloudflare platform plugin with curated skills for Workers, Wrangler, and Agents SDK plus the official Cloudflare API MCP server.
-
CrowdStrike Falcon Foundry development skills for building cybersecurity applications on the Falcon platform. Includes UI development, collections, functions, workflows, API…
-
Codex Security workflows for security scans, analysis, and investigation.
-
CrowdStrike Falcon Fusion skills for authoring, deploying, and executing Fusion workflows. Includes live action discovery, YAML authoring with schema validation, workflow import…
-
Build with OpenAI APIs, Agents SDK, and ChatGPT Apps, and create and save OpenAI API keys from Codex.
Publicado en Community GitHub marketplaces (5)
-
One system around coding agents to run, verify, recover, and hand off software work.
-
Build high-quality MCP servers for LLM integrations
-
Build MCP (Model Context Protocol) servers on Cloudflare Workers with tools, resources, and prompts.
-
Liongard config visibility: sync your estate offline, then drift-check and search it from one CLI.
-
Gives AI agents the function they asked for, not the file. Commercial use needs a license.
Publicado en Copilot CLI: github/awesome-copilot (5)
-
Complete toolkit for building Model Context Protocol (MCP) servers in Go using the official github.com/modelcontextprotocol/go-sdk. Includes instructions for best practices, a…
-
Complete toolkit for building Model Context Protocol (MCP) servers in TypeScript/Node.js using the official SDK. Includes instructions for best practices, a prompt for generating…
-
Complete toolkit for building Model Context Protocol (MCP) servers in Kotlin using the official io.modelcontextprotocol:kotlin-sdk library. Includes instructions for best…
-
Safe BLE diagnostics, evidence workflows, and guarded automation for AI agents.
-
Interactive GitHub Copilot canvas for discovering, connecting, and managing hosted MCP servers from an Azure Connector Namespace.
Publicado en Copilot CLI: github/copilot-plugins (5)
-
Advanced Security plugin for GitHub Copilot.
-
mcp-apps
Generate MCP App widgets for MCP tools. Produces self-contained HTML widgets using the MCP Apps protocol.
-
Toolkit for building Microsoft 365 Copilot declarative agents — scaffolding, JSON manifest development, and capability configuration.
-
Build Power Apps Canvas Apps using the Canvas Authoring MCP server.
-
model-apps
Build and deploy Power Apps generative pages for model-driven apps with specialist agents for planning, entity creation, and parallel code generation. Requires PAC CLI >= 2.7.0…
Publicado en Cursor: cursor/plugins (5)
-
Let Grok Bot reach MCP servers on your private Tailscale network: connect your own tailnet, or your team's company tailnets turned on by a team admin, with each member using their…
-
Build apps, scripts, and automations with the TypeScript SDK.
-
Query and remediate compliance tests, controls, frameworks, risks, and vulnerabilities in Vanta.
-
Fan large tasks out across parallel cloud agents with planners, workers, verifiers, and structured handoffs.
-
playwright-mcp io.github.microsoft/playwright-mcp
Playwright Tools for MCP
Publicado en Docker MCP Catalog (4)
-
stackhawk com.stackhawk/stackhawk
An MCP server that provides interaction with StackHawk's security scanning platform.
-
Real-time network monitoring, security analysis, and firewall management through 28 specialized tools. Access security alerts, network flows, device status, and firewall rules…
-
Give your AI agents trusted access to the full Postman platform.
-
npm-sentinel-mcp io.github.Nekzus/npm-sentinel-mcp
Advanced NPM analysis: Recursive security scanning, ecosystem awareness, and deep insights.
Publicado en Official MCP Registry (5)
-
Secure MCP server framework with 23 security layers and ML threat detection. Zero deps.
-
Local secret & credential checks for AI-assisted dev — runs on your machine, results redacted.
-
guardrails io.github.ExpertVagabond/guardrails
AI Agent Guardrails MCP server - security layer
-
secureflows-mcp io.github.michal-lefler/secureflows-mcp
MCP server for secureFlows: token-free URL builders and integration-linting tools for AI agents.
-
ai-agent-firewall com.fidacy/ai-agent-firewall
Every agent action watched, every money-moving one gated, every verdict independently verifiable.
Publicado en PyPI (MCP servers) (5)
-
Sniff out what your AI tools are hiding: local security checks for MCP servers (hidden instructions, known malware, leaked secrets, rug pulls).
-
mcp-safeguard com.cognivators/mcp-safeguard
MCP server security scanner: detects prompt injection, credential leaks, SSRF, tool poisoning.
-
MCP server for Mipiti — AI-powered security posture platform
-
Guard Core security MCP: SecurityConfig validation, docs search, live threat detection.
-
awslabs.security-agent-mcp-server
An AWS Labs Model Context Protocol (MCP) server for AWS Security Agent — automated security scanning, penetration testing, and remediation
Publicado en npm registry (MCP servers) (5)
-
ai-agent-firewall com.fidacy/ai-agent-firewall
Every agent action watched, every money-moving one gated, every verdict independently verifiable.
-
security-proxy io.github.4hmetuyar/security-proxy
MCP gateway: many servers, one policy, lethal-trifecta blocking, PII masking, audit log
-
agent-security-scanner-mcp io.github.sinewaveai/agent-security-scanner-mcp
Security layer for AI agents: blocks prompt injection, detects fake packages, scans vulnerabilities.
-
HSM-backed vault secrets for AI agents (JIT fetch) plus prompt-injection and threat scanning.
-
mcp com.dechonet/mcp
34 security tools for AI agents: phishing links, exposure maps, DNS, SSL, PQC, history, pivots.
Encontrados por significado, no por código ni repositorio compartidos: los plugins similares siguen siendo productos distintos, y esto no es una reseña ni una recomendación.
¿Quieres esta marca para tu plugin en nuestro catálogo?
Demuestra que lo mantienes con un archivo en su repositorio, un archivo en tu dominio o un registro DNS, y podrás mostrar esta marca en la ficha, con banners en vivo para tu web y tu README. Cómo funciona la verificación
Además recibirás avisos cuando un marketplace lo publique, lo retire, cambie su marca verificada o lo que pide, y su endpoint remoto quedará monitorizado como un servicio web.
Añada un banner dinámico a su README o sitio web
Muestre datos actualizados del catálogo en su sitio web o README de GitHub. Elija un banner dinámico o una insignia compacta.
Datos de Official MCP Registry. Las cifras proceden de nuestros propios recorridos periódicos por los marketplaces, leída por última vez el . No publicamos datos de contacto de los editores de plugins.