inspeximus: agent memory with provenance, GDPR erasure and a tamper-evident audit trail
Self-correcting agent memory: recall, supersede, revert, forget, GDPR erasure, audit receipts.
Servidor MCP · de DanceNitra
Resumen
inspeximus: agent memory with provenance, GDPR erasure and a tamper-evident audit trail es un servidor MCP publicado por DanceNitra. Marketplaces que leemos y que lo publican: 2 (Official MCP Registry, Community GitHub marketplaces). El último cambio que registramos fue el 2026-10-12. Según nuestra pasada por los marketplaces del 2026-10-13.
Qué pide
- Se ejecuta en tu equipo
- Ajustes: 4
- Hooks declarados: 5
Lo que declara, pide y ejecuta, completo
Instale solo plugins de desarrolladores en los que confíe. Mostramos lo que publican los marketplaces y no probamos plugins.
Paquete
PyPI inspeximus (inspeximus en PyPI)
- Descargas de PyPI por semana: 2 009 (2026-10-13)
- Descargas de PyPI por mes: 14 264 (2026-10-13)
- Última versión en PyPI: 3.18.0, publicada el 2026-10-11
Sin vulnerabilidades conocidas en OSV para 3.18.0 (comprobado el 2026-10-13)
Los datos de PyPI proceden de pypi.org y las descargas de PyPI de pypistats.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
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 usted ni probamos plugins.
Como servidor MCP local: paquete PyPI
Generado a partir de lo que declara Official MCP Registry.
claude mcp add --transport stdio inspeximus -- uvx --from "inspeximus[mcp]" inspeximus mcp[mcp_servers.inspeximus]
command = "uvx"
args = ["--from", "inspeximus[mcp]", "inspeximus", "mcp"]{
"mcpServers": {
"inspeximus": {
"command": "uvx",
"args": [
"--from",
"inspeximus[mcp]",
"inspeximus",
"mcp"
]
}
}
}Ajustes opcionales que también indica: INSPEXIMUS_ECHO_GUARD, INSPEXIMUS_EMBED_MODEL, INSPEXIMUS_EMBED_URL, INSPEXIMUS_PATH.
Como plugin de Claude Code
Generado a partir de lo que declara Community GitHub marketplaces.
/plugin marketplace add dancenitra/inspeximus
/plugin install inspeximus@inspeximusDónde está publicado
| Marketplace | Estado | Versión | Cifras | Verificado | Visto por primera vez |
|---|---|---|---|---|---|
| Official MCP Registry (Abrir el registro) | Publicado | 3.18.0 | Descargas por mes (PyPI): 14 264 Descargas por semana (PyPI): 2 009 Forks (GitHub): 1 Estrellas (GitHub): 8 |
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.
También figura en un marketplace de la comunidad
| Marketplace | Repositorio | Estrellas (GitHub) |
|---|---|---|
| inspeximus | dancenitra/inspeximus | 8 |
Qué contiene el paquete
Tal como se publica en Community GitHub marketplaces.
Servidores MCP: 1
inspeximus
Hooks: 5
PostToolUsePreToolUseSessionEndSessionStartUserPromptSubmit
Qué cambió
- Apareció en un nuevo marketplace: Community GitHub marketplaces
- Community GitHub marketplaces: apareció
- Official MCP Registry: publicó la versión 3.18.0 (antes 3.17.1)
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.
-
veracium io.github.veracium-ai/veracium
Provenance-aware memory for AI agents: quarantine, abstention gate, supersession-with-history.
-
Agent memory that refuses to guess: evidence-gated recall, exact-source reads, verifiable deletion.
-
verifiable-memory io.github.Mars-proj/verifiable-memory
Memory for AI agents that can't hallucinate — cited or abstains, provable forget, deterministic.
-
Bitemporal memory for AI agents with point-in-time recall and tamper-evident audit history.
-
al-buddy-memory io.github.flytomoon/al-buddy-memory
Governed local memory for AI agents: facts are retired, not overwritten, and every call is audited.
-
memory-pulse io.github.t-crew/memory-pulse
Give any agent self-improving memory you can trust in production. Built-in memory security.
-
agent-memory-mcp io.github.kira-autonoma/agent-memory-mcp
Agent memory MCP server with provenance tracking, decay-weighted recall, and feedback loops.
-
Auditable memory for AI agents: provenance, cascade retraction, conflict refusal
-
Managed long-term memory for AI agents, with evolving facts and relevant retrieval through MCP.
-
Persistent local memory for coding agents: temporal knowledge graph, procedural and episodic recall
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)
-
engram io.github.tstockham96/engram
Intelligent agent memory with automatic extraction, consolidation, and bi-temporal recall.
-
agent-knowledge io.github.keshrath/agent-knowledge
Cross-session memory for AI agents - knowledge graph, scoring, semantic search
-
Save 60-90% on LLM token costs with intelligent memory compression. agent-memory automatically compresses tool output into structured observations, shares context across agents…
-
Persistent memory that survives across sessions. Hipocampus gives your agent a 3-tier memory system (hot/warm/cold) with a self-compressing 5-level compaction tree. Every session…
-
Persistent semantic memory for Claude Code. Stores knowledge in a local ChromaDB vector database and automatically retrieves relevant context on every message using Ollama bge-m3…
Publicado en Claude Code: claude-plugins-official (5)
-
Continuous memory for Claude Code. Extracts, summarizes, and compresses conversations into tiered daily logs. Claude remembers what you did yesterday.
-
Skills for working with Langfuse, the open-source LLM engineering platform for tracing, prompt management, and evaluation.
-
Agentforce Agent Development Life Cycle — author, discover, scaffold, deploy, test, and optimize .agent files
-
Build, deploy, and operate AI agents on AWS. Skills for scaffolding agents with Amazon Bedrock AgentCore, connecting tools, memory, policies, evaluation, debugging, and production…
-
Skills for adding DeepEval evaluations, tracing, datasets, Confident AI reports, and iterative improvement loops to AI applications.
Publicado en Claude: knowledge-work-plugins (5)
-
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…
-
DataRobot skills for AI/ML workflows — model training, deployment, predictions, feature engineering, monitoring, explainability, data preparation, App Framework CI/CD, and…
-
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…
-
AI-first project auditor and re-engineer based on the 9 design principles and 7 design patterns from the TechWolf AI-First Bootcamp
Publicado en Codex: openai-curated (openai/plugins) (5)
-
CrowdStrike Falcon Foundry development skills for building cybersecurity applications on the Falcon platform. Includes UI development, collections, functions, workflows, API…
-
Skills for NVIDIAs ecosystem spans GPU acceleration, CUDA, AI agents, inference, robotics, Physical AI, Omniverse, and simulation. This plugin helps you understand the pieces…
-
Notion workflows for implementation planning, research synthesis, meeting preparation, and knowledge capture.
-
Available for US1 customers only. Analyze, investigate, and act on your Datadog telemetry directly from ChatGPT using natural language. Ask questions about your production…
-
Build with OpenAI APIs, Agents SDK, and ChatGPT Apps, and create and save OpenAI API keys from Codex.
Publicado en Community GitHub marketplaces (5)
-
al-buddy-memory io.github.flytomoon/al-buddy-memory
Governed local memory for AI agents: facts are retired, not overwritten, and every call is audited.
-
Bitemporal memory for AI agents with deterministic supersession, point-in-time recall, local MCP, erasure proofs, and tamper-evident history.
-
agent-knowledge io.github.keshrath/agent-knowledge
Cross-session memory for AI agents - knowledge graph, scoring, semantic search
-
Memory that abstains instead of guessing. Searches your project's own notes and decisions, marks a retracted claim as superseded, and refuses when nothing clears the threshold.
-
Persistent decision memory for AI coding agents: rationale, rejected approaches, and entity history.
Publicado en Copilot CLI: github/awesome-copilot (5)
-
Three-layer verification pipeline for AI output. Extracts claims, finds sources, and flags hallucination risks so humans can verify before acting.
-
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…
-
Safe BLE diagnostics, evidence workflows, and guarded automation for AI agents.
-
Run a lightweight, role-separated AI development team with flexible tools, developer-selected models, proportionate planning, and optional QA.
-
Three-agent workflow for orchestrated software delivery with an orchestrator plus implementation and QA subagents.
Publicado en Copilot CLI: github/copilot-plugins (5)
-
Toolkit for building Microsoft 365 Copilot declarative agents — scaffolding, JSON manifest development, and capability configuration.
-
workiq
Query Microsoft 365 data with natural language — emails, meetings, documents, Teams messages, and more.
-
workiq-productivity
WorkIQ productivity skills powered by the local WorkIQ CLI — read-only insights across email, meetings, calendar, Teams, SharePoint, projects, and people.
-
Advanced Security plugin for GitHub Copilot.
-
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)
-
Incremental transcript-driven memory updates for AGENTS.md using high-signal bullet points only.
-
Capture, search, and organize notes and collections.
-
Iterative self-referential AI loops using the Ralph Wiggum technique.
-
Fan large tasks out across parallel cloud agents with planners, workers, verifiers, and structured handoffs.
-
Patterns for designing CLIs that coding agents can run reliably: flags, help with examples, pipelines, errors, idempotency, dry-run.
Publicado en Docker MCP Catalog (5)
-
mcp-neo4j-memory io.github.neo4j-contrib/mcp-neo4j-memory
MCP Neo4j Knowledge Graph Memory Server
-
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
-
Knowledge graph-based persistent memory system.
-
A Model Context Protocol server for Omi interaction and automation. This server provides tools to read, search, and manipulate Memories and Conversations.
Publicado en Official MCP Registry (5)
-
veracium io.github.veracium-ai/veracium
Provenance-aware memory for AI agents: quarantine, abstention gate, supersession-with-history.
-
Agent memory that refuses to guess: evidence-gated recall, exact-source reads, verifiable deletion.
-
verifiable-memory io.github.Mars-proj/verifiable-memory
Memory for AI agents that can't hallucinate — cited or abstains, provable forget, deterministic.
-
Bitemporal memory for AI agents with point-in-time recall and tamper-evident audit history.
-
al-buddy-memory io.github.flytomoon/al-buddy-memory
Governed local memory for AI agents: facts are retired, not overwritten, and every call is audited.
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.
¿Es tu plugin?
Añádelo a tus proyectos y demuestra que lo mantienes con un archivo en su repositorio, un archivo en tu dominio o un registro DNS. 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. Datos de Community GitHub marketplaces. 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.