DidWork
Verify that an agent's claimed outcome actually happened, using independently gathered evidence
Servidor MCP · de didwork.sh
Resumen
DidWork es un servidor MCP publicado por didwork.sh. Marketplaces que leemos y que lo publican: 1 (Official MCP Registry). El último cambio que registramos fue el 2026-10-15. Según nuestra pasada por los marketplaces del 2026-10-24.
Qué pide
- Se ejecuta en tu equipo
- Secretos: 1
- Ajustes: 2
Requiere: DIDWORK_API_KEY (secreta)
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.
Paquete
npm @didwork/mcp (@didwork/mcp en npm)
- Descargas de npm por semana: 82 (2026-10-15)
- Descargas de npm por mes: 1 047 (2026-10-15)
- Última versión en npm: 0.1.1, publicada el 2026-09-23
Sin vulnerabilidades conocidas en OSV para 0.1.1 (comprobado el 2026-10-23)
Los datos de npm proceden del registro público de npm (registry.npmjs.org, api.npmjs.org). Cada cifra es del propio registro y nunca se suma a otra. Un registro que no publica una cifra no muestra ninguna: sin cifra no es cero. Los registros de vulnerabilidades proceden de OSV.dev (CC BY 4.0) y solo se refieren a la versión declarada; un listado sin versión declarada no recibe respuesta. No analizamos código.
Funciona con
- Claude Code
- Codex
- Cursor
- VS Code
- Copilot CLI
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 local: paquete npm
Generado a partir de lo que declara Official MCP Registry.
claude mcp add --env "DIDWORK_API_KEY=<YOUR_DIDWORK_API_KEY>" --transport stdio didwork -- npx -y @didwork/mcp[mcp_servers.didwork]
command = "npx"
args = ["-y", "@didwork/mcp"]
[mcp_servers.didwork.env]
DIDWORK_API_KEY = "<YOUR_DIDWORK_API_KEY>"{
"mcpServers": {
"didwork": {
"command": "npx",
"args": [
"-y",
"@didwork/mcp"
],
"env": {
"DIDWORK_API_KEY": "<YOUR_DIDWORK_API_KEY>"
}
}
}
}Sustituya los valores entre corchetes angulares por los suyos. Mostramos los nombres de los ajustes, nunca valores.
Ajustes opcionales que también indica: DIDWORK_BASE_URL.
Dónde está publicado
| Marketplace | Estado | Versión | Cifras | Verificado | Visto por primera vez |
|---|---|---|---|---|---|
| Official MCP Registry (Abrir el registro) | Publicado | 0.1.1 | Descargas por mes (npm): 1 047 Descargas por semana (npm): 82 |
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.
Qué cambió
Nada ha cambiado en este plugin desde que lo seguimos.
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.
-
Checks an AI agent's 'done' against the files and URLs it claims. Missing = FALSE_DONE.
-
Check claimed and solved agent work, then coordinate through a signed public board.
-
Outcome-verified watchdog for scheduled agents
Watchdog that verifies scheduled agents' artifacts itself — never the claim.
-
Checks whether an agent's actions actually happened, against the destination's own records.
-
Deterministic JSON checks with signed evidence and x402-paid execution
-
mcp io.github.Postcept/mcp
Verify agent actions against the system of record and get signed completion receipts.
-
Agent Output Verifier by Sarnai
Verify an agent's output before you pay: JSON Schema + rules, signed receipts. Free during launch.
-
Independent effect verification and signed receipts for consequential AI agent actions.
-
Now part of GAIP Witness: records a task outcome and caller-supplied costs.
-
MCP Verification Gate: check an MCP server or an A2A agent before you connect or delegate
Check an A2A agent before you delegate, or an MCP server's measured conduct. Free, no key.
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)
-
Offline Ed25519 receipt verifier — checks signed decision receipts, agent manifests, and audit bundles without contacting any server.
-
AI agent evaluation sandbox for Claude Code. Holdout scenario testing with Doer/Judge/Adversary/Observer roles, probabilistic satisfaction scoring, and append-only JSONL audit…
-
Strale agent skills with remote MCP connector for Strale platform integration.
-
SCOPE - Security, Compliance & Operational Policy Evaluation - A Claude plugin that runs deterministic pre-flight compliance evaluation on agentic workflows. Maps every MCP tool…
-
Real-time dashboard showing Claude Code subagent status and activity Analyze their performances and offer improvements
Publicado en Claude Code: claude-plugins-official (5)
-
Agentforce Agent Development Life Cycle — author, discover, scaffold, deploy, test, and optimize .agent files
-
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.
-
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…
-
Dynatrace observability skills: DQL query patterns, application and infrastructure monitoring, log analysis, problem investigation, and incident response workflows, with the…
-
Detect AI agents in your codebase and instrument them with Pendo Agent Analytics via the best-fit path: Python SDK, TypeScript SDK, client-side trackAgent, or the Conversations…
Publicado en Claude: knowledge-work-plugins (5)
-
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…
-
Skills for working with Langfuse, the open-source LLM engineering platform for tracing, prompt management, and evaluation.
-
Connects Claude Code to the Synthflow AI voice-agent platform through its hosted MCP server, with skills for reviewing calls and auditing agent prompts, plus a docs-search…
-
Hosted MCP server for AI-assisted Grafana Cloud observability — no local installation required.
-
Official SigNoz plugin for MCP setup, docs, queries, dashboards, and alerts
Publicado en Codex: openai-curated (openai/plugins) (5)
-
CrowdStrike Falcon Fusion skills for authoring, deploying, and executing Fusion workflows. Includes live action discovery, YAML authoring with schema validation, workflow import…
-
Evaluate Codex skills and plugins from chat with a beginner-friendly start command, local-first reports, token budget explanations, and guided benchmarking.
-
PostHog gives your AI agent direct access to your product analytics, feature flags, experiments, error tracking, surveys, logs, and LLM analytics. Ask questions about your data…
-
Codex Security workflows for security scans, analysis, and investigation.
-
Available for US1 customers only. Analyze, investigate, and act on your Datadog telemetry directly from ChatGPT using natural language. Ask questions about your production…
Publicado en Community GitHub marketplaces (5)
-
Make a coding agent prove it: run the repo's real tests, typecheck and lint before it says done.
-
Find and fix reliability and safety gaps in agent code, across nine agent SDKs.
-
An easy way to force agent to think again if it's statement that the "Job is done and production ready" is actually done - usually it's not. Thanks to this command you don't have…
-
protect-mcp com.scopeblind/protect-mcp
Fail-closed Cedar policy gate + Ed25519 signed receipts for agent tool calls. Denies on any error.
-
watch-skill io.github.oxbshw/watch-skill
Watch video and live sessions, keep timestamped evidence, and verify an agent's own work.
Publicado en Copilot CLI: github/awesome-copilot (5)
-
A runtime-portable 5-agent quality gate that adjudicates text artifacts before they ship. Five role-conditioned LLM deliberators run a 2-round async protocol with cross-read…
-
Three-agent workflow for orchestrated software delivery with an orchestrator plus implementation and QA subagents.
-
Safe BLE diagnostics, evidence workflows, and guarded automation for AI agents.
-
Three-layer verification pipeline for AI output. Extracts claims, finds sources, and flags hallucination risks so humans can verify before acting.
-
See a live map of the Copilot agents on your computer, their sub-agents, their commands, and where their data goes.
Publicado en Copilot CLI: github/copilot-plugins (5)
-
workiq-productivity
WorkIQ productivity skills powered by the local WorkIQ CLI — read-only insights across email, meetings, calendar, Teams, SharePoint, projects, and people.
-
workiq
Query Microsoft 365 data with natural language — emails, meetings, documents, Teams messages, and more.
-
Toolkit for building Microsoft 365 Copilot declarative agents — scaffolding, JSON manifest development, and capability configuration.
-
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.
Publicado en Cursor: cursor/plugins (5)
-
CLI-backed repo compatibility scans plus agents that audit startup, validation, and docs against reality.
-
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.
-
Search company knowledge and draft verified answers.
-
Work with PostHog from chat: query product analytics and run SQL, manage feature flags and experiments, triage error tracking issues, and review session replays, surveys, and…
Publicado en Docker MCP Catalog (5)
-
Wayfound’s MCP server allows business users to govern, supervise, and improve AI Agents.
-
Server-enforced workflow discipline for AI agents: work items, dependency graphs, quality gates
-
A unified MCP proxy that aggregates multiple MCP servers into one interface, enabling seamless tool discovery and management across all your AI interactions. Manage all your MCP…
-
The Official Model Context Protocol (MCP) server for Kagi Search & other tools.
-
Read and score Opik traces, experiments, datasets and prompts from your AI assistant.
Publicado en Official MCP Registry (5)
-
Checks an AI agent's 'done' against the files and URLs it claims. Missing = FALSE_DONE.
-
Check claimed and solved agent work, then coordinate through a signed public board.
-
Outcome-verified watchdog for scheduled agents
Watchdog that verifies scheduled agents' artifacts itself — never the claim.
-
Checks whether an agent's actions actually happened, against the destination's own records.
-
Deterministic JSON checks with signed evidence and x402-paid execution
Publicado en PyPI (MCP servers) (5)
-
Checks what an agent did NOT read. Coverage over a retrieval step or a folder.
-
Read-only MCP server over Verdict QA state: verdicts, findings, flaky quarantine, history.
-
Unified MCP server for AgenticLens and Agentic Chaos capabilities.
-
Read, measure and explain LLM eval runs of a digline suite. Cannot promote a baseline.
-
Incident management, on-call scheduling, and intelligent analysis powered by Rootly.
Publicado en npm registry (MCP servers) (5)
-
A deterministic verification engine for agents. Proves a fix: fails on the old code, passes on new.
-
Snapshot tests and CI for agent workflows: record a run, replay it at 0 tokens, diff for drift.
-
protect-mcp com.scopeblind/protect-mcp
Fail-closed Cedar policy gate + Ed25519 signed receipts for agent tool calls. Denies on any error.
-
Check an MCP server, skill or plugin before your agent uses it: tool text on record, changes graded.
-
workday-mcp io.github.chrischall/workday-mcp
Read-only Workday for Claude — fetch tasks, pay, benefits via your signed-in session
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.
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.