mcp server
self-inspect-mcp
Send a thought, get one metathought that makes your agent inspect its own assumptions. Keyless.
Description as published by the maintainer. Source
- version 0.1.1
- active
active — Most recent push to the repository was 2026-06-13.
What this server can do
1 function, named and described by the server itself. Parameter names are shown because they say more about what a function does than its name usually does.
self_inspect(thought)- Self-Inspect. Express a thought, or describe the task you are working on, and you always get back ONE metathought: a short abstract question that makes you inspect your own task and assumptions before continuing. Use it whenever you want a self-check: after forming a hypothesis, before committing to an answer, when a long chain feels like it has drifted, when you notice you are agreeing to please, or when you are about to assert something from memory. There is no failure case: it always returns a metathought to question yourself with, selected by a transparent heuristic over an open CSV (no LLM). Keyless and free. DO NOT call for factual lookups or as a substitute for doing the task. Absorb the question and act on it; do not echo it verbatim to the user. Required: thought.
Last successful function declaration observed on . Source: https://api.ejentum.com/self-inspect-mcp. We list what the server declared; we do not call any of these functions.
Endpoint status observed on . Source: https://api.ejentum.com/self-inspect-mcp.
Signals
These are separate measurements of different things. They are deliberately not combined into one score, because a popularity number that mixes website traffic with saves and stars cannot be checked or acted on.
| Signal | Value | What it measures | Window | Observed | Source |
|---|---|---|---|---|---|
| GitHub stars | 7 | Number of GitHub accounts that bookmarked this repository since it was created. It is a bookmark count, not installs, not active users and not quality. | cumulative, all time | GitHub | |
| Last commit | 2026-06-13 | Date of the most recent push to any branch. This is the strongest cheap indicator of whether the project is still maintained. | point in time | GitHub | |
| Open issues | 0 | Open issues plus open pull requests, as GitHub counts them together. A high number can mean an active project or an abandoned one. | as of fetch | GitHub | |
| Latest published version | 0.1.1 | Latest version string the maintainer published to the registry. | as of fetch | Model Context Protocol | |
| Registry record last updated | 2026-06-11 | When the registry record was last updated by its maintainer. | point in time | Model Context Protocol | |
| License | MIT | Licence GitHub detected in the repository. Detection can be wrong; the LICENSE file is authoritative. | as of fetch | GitHub | |
| First listed in the MCP Registry | 2026-06-11 | Date this server was first published to the official MCP Registry. Not a usage or quality measure. | point in time | Model Context Protocol | |
| repository status | active | The repository exists on GitHub and is not archived. This says nothing about how recently it was worked on. | as of fetch | GitHub | |
| mcp tools declared | 1 tools | Number of functions the server itself declared when asked to list them. This is what the server offers an agent, not a measure of how well any of them work. | as of probe | api.ejentum.com | |
| mcp endpoint status | ok | The server listed 1 function when asked. | as of probe | api.ejentum.com |
Where to get it
Related, by what their authors tagged them
-
io.github.ejentum/ejentum-mcp
— last commit 2026-06-11, shares agentic-ai, ejentum
Reasoning, code, anti-deception, memory harness MCP tools. Stdio or HTTPS api.ejentum.com/mcp
-
ai.nocturnus/logic-server
— last commit 2026-04-17, shares agentic-ai, agents, reasoning
Agent reasoning, memory, and token-optimized context for AI applications.
-
Grounded Reasoning
— last commit 2026-07-06, shares agents, reasoning
Verify multi-hop relational claims before an agent asserts them — zero tokens, with proof paths.
-
Graqle
— last commit 2026-08-04, shares reasoning
Dev intelligence layer: 7 MCP tools for graph-powered codebase reasoning.
-
ai.aliengiraffe/spotdb
— last commit 2026-08-05, shares agentic-ai, agents
Ephemeral data sandbox for AI workflows with guardrails and security
-
Sema
— last commit 2026-08-04, shares agentic-ai, agents
MCP tools for Sema — eval, compile, build, format, and docs for a Lisp with LLM primitives.
-
com.stayker/1stay
— last commit 2026-08-03, shares agentic-ai, agents
Hotel booking MCP server. Search, book, and manage reservations across 250K+ properties worldwide.
-
feiskyer-claude-code-settings-brainstorming
— last commit 2026-07-27, shares agentic-ai, agents
Explore user intent, requirements, and design options through collaborative dialogue before implementation. Use before…
-
feiskyer-claude-code-settings-codex-skill
— last commit 2026-07-27, shares agentic-ai, agents
Leverage OpenAI Codex/GPT models for autonomous code implementation, code review, and plan review. Triggers: "codex", "…
-
feiskyer-claude-code-settings-deep-research
— last commit 2026-07-27, shares agentic-ai, agents
Multi-agent research orchestration: split a research goal into parallel sub-goals, run each via headless `claude -p` su…
These share tags the maintainers applied themselves, such as agentic-ai, ejentum, agents, reasoning. Common tags like "mcp" or "ai" are ignored for this: agreeing with six hundred other projects is not a similarity.
This is not a recommendation and not a test result. It is a map of what the authors said their work is about.
How the author describes it
Topics the maintainer set on GitHub: agentic-ai, agents, ai-agents, ejentum, llm, mcp, metacognition, model-context-protocol, reasoning, self-reflection.
This record as data
Every field on this page, with its source and observation date, is in the catalog JSON. Fetch the whole kind at once instead of parsing this HTML.
GET /api/v1/entries/mcp_server.json