# LoopingAgent (remote · loopingagent.com)

English blog + agentic AI architect profile (Paris): search, full text, projects, booking.

- Trust score: 75/100 (medium)
- Change this week: +3
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-09-20

## Components

- remote · `loopingagent.com`: 75/100 (this document), [markdown](https://verifymcp.io/servers/com-loopingagent-loopingagent-mcp/api-mcp.md), [page](https://verifymcp.io/servers/com-loopingagent-loopingagent-mcp/api-mcp)

## Channel facts

- Endpoint: `https://loopingagent.com/api/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `0.3.0`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-09-20.

- **Endpoint Security**: 57/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation not fully verified: no authorisation is required to call this server, and 9 tool(s) never declared a destructiveHint. The MCP spec treats an absent hint as destructive by default, so we cannot call this surface safe.
  - HTTPS is enforced; there's no plaintext access path.
  - HSTS check failed: the Strict-Transport-Security header is absent.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 83/100
  - AI-judged instruction clarity (excellent).
  - Tool/resource definitions use about 775 tokens (~86/item across 9 items; 9 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 77/100
  - Stability observed for 23 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 9 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 9 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 60/100
  - Spec-recency check failed: implements MCP spec 2025-06-18; the latest is 2026-07-28.

## Install

### How do I install the LoopingAgent MCP server?

LoopingAgent is a hosted endpoint at https://loopingagent.com/api/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add --transport http com-loopingagent-loopingagent-mcp 'https://loopingagent.com/api/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "com-loopingagent-loopingagent-mcp": {
      "url": "https://loopingagent.com/api/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "com-loopingagent-loopingagent-mcp": {
      "type": "http",
      "url": "https://loopingagent.com/api/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.com-loopingagent-loopingagent-mcp]
url = "https://loopingagent.com/api/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "com-loopingagent-loopingagent-mcp": {
      "type": "remote",
      "url": "https://loopingagent.com/api/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add com-loopingagent-loopingagent-mcp --url 'https://loopingagent.com/api/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  com-loopingagent-loopingagent-mcp:
    url: "https://loopingagent.com/api/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "com-loopingagent-loopingagent-mcp": {
      "Transport": "http",
      "Url": "https://loopingagent.com/api/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add com-loopingagent-loopingagent-mcp -t streamable-http -u 'https://loopingagent.com/api/mcp'
```

### Other

```json
{
  "mcpServers": {
    "com-loopingagent-loopingagent-mcp": {
      "type": "http",
      "url": "https://loopingagent.com/api/mcp"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-09-20 (score 75, +1)

- [cosmetic] “list_projects” reworded the description of “status”

### 2026-09-17 (score 74, +1)

No change was recorded against any check on this day. Stability & Change Management went from 63 to 67. That category is still filling its 30-day observation window: 19 days of observed history at the previous scan, 20 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-15 (score 73, +1)

No change was recorded against any check on this day. Stability & Change Management went from 57 to 60. That category is still filling its 30-day observation window: 17 days of observed history at the previous scan, 18 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-13 (score 72, +1)

No change was recorded against any check on this day. Stability & Change Management went from 50 to 53. That category is still filling its 30-day observation window: 15 days of observed history at the previous scan, 16 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-11 (score 71, +1)

- [security] Tool “get_article” rewrote its description, which is the text the model reads
- [security] Tool “list_articles” rewrote its description, which is the text the model reads
- [functional regression] Schema quality: 69 → 85
- [functional] Server version: 0.1.0 → 0.3.0
- [functional] New tool “get_project”
- [functional] New tool “list_categories”
- [functional] New tool “list_projects”
- [functional] New tool “search_articles”
- [cosmetic] “get_article” added an optional parameter “include_content”
- [cosmetic] “list_articles” added an optional parameter “limit”

### 2026-09-09 (score 70, +1)

- [security] Tool “get_skill” rewrote its description, which is the text the model reads

### 2026-09-08 (score 69, +1)

No change was recorded against any check on this day. Stability & Change Management went from 33 to 37. That category is still filling its 30-day observation window: 10 days of observed history at the previous scan, 11 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-05 (score 68, +1)

No change was recorded against any check on this day. Stability & Change Management went from 23 to 27. That category is still filling its 30-day observation window: 7 days of observed history at the previous scan, 8 at this one. The score rises as the window fills, whether or not the server changes.

## MCP tools (9)

### `get_profile` (~59 tokens)

Full professional profile of Laurent Knauss: title, location, availability, contact email, social profiles (GitHub, LinkedIn, X), certifications, and Cal.com booking link. Use this first to understand who he is and how to reach him.

### `get_skill` (~63 tokens)

Laurent Knauss' technical skills, grouped by domain (Agentic AI, RAG & Voice AI, Software engineering & Cloud, Automation & tooling). Each skill has a label and an optional short detail. Use this to assess fit for AI/agentic development roles.

### `list_articles` (~94 tokens)

List articles published on loopingagent.com (English technical blog: agentic AI, MCP, LangGraph, TypeScript, blockchain). Returns slug, title, category and description for each. Use search_articles to find articles on a topic, and get_article to read one in full.

Input parameters:

- `category` (string): Filter articles by category.
- `limit` (number): Maximum number of articles to return (default: all of them).

### `get_article` (~117 tokens)

Get a single article from loopingagent.com: metadata (category, description, cover, canonical URL), the FULL plain-text content (so the agent can quote and cite it accurately) and 3 related articles. Use list_articles or search_articles first to find the slug.

Input parameters:

- `include_content` (boolean): Include the full article text (default: true). Set to false for metadata only, which is cheaper.
- `slug` (string, required): Article slug. Ex: browser-automation, agentic-commerce-protocol, langgraph-generative-ui

### `list_projects` (~103 tokens)

Projects built and shipped by Laurent Knauss (agentic AI products and full-stack web apps), with domain, live status, one-line positioning and tech stack. Use it to assess his delivery track record — get_project returns the full description.

Input parameters:

- `category` (string): Filter by project family: ai (agentic AI) or web.
- `status` (string): Filter by status: live (deployed in production) or oss (open source, not deployed).

### `get_project` (~73 tokens)

Full details of one project shipped by Laurent Knauss: positioning, complete description, tech stack, live URL and status. Use list_projects first for the exact names.

Input parameters:

- `name` (string, required): Project name. Ex: AgentRecruteur, BullionRadar, ActionArgent, StreetBodies, VersatileAgent

### `search_articles` (~142 tokens)

Full-text search across every article on loopingagent.com (title, description and body text). Returns the most relevant matches with a snippet of the matching passage, ranked by relevance. Use this to find an article to quote or cite on a topic — ex. 'ERC-4337 paymaster', 'Golang pointers', 'evaluating LLM applications', 'MCP server'.

Input parameters:

- `category` (string): Restrict the search to one category.
- `limit` (number): Maximum number of results (default: 5, max: 20).
- `query` (string, required): Search terms (keywords, topic or technology). Multi-word queries are scored per term.

### `list_categories` (~43 tokens)

List the loopingagent.com article categories with their article counts and slugs. Use it to browse the blog by theme (Agentic AI, blockchain) before fetching an article.

### `book_call` (~81 tokens)

Get the booking link to schedule a free 30-minute call with Laurent Knauss (Cal.com). The agent should present this link to the user so they can pick a slot. Optional topic hint is allowed but the actual slot selection happens on Cal.com.

Input parameters:

- `topic` (string): Optional topic for the call (e.g. 'agentic AI project').

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/com-loopingagent-loopingagent-mcp/api-mcp#diagnostics

## Score history

- 2026-09-20: 75
- 2026-09-19: 74
- 2026-09-18: 74
- 2026-09-17: 74
- 2026-09-16: 73
- 2026-09-15: 73
- 2026-09-14: 72
- 2026-09-13: 72
- 2026-09-12: 71
- 2026-09-11: 71
- 2026-09-10: 70
- 2026-09-09: 70
- 2026-09-08: 69
- 2026-09-07: 68
- 2026-09-06: 68
- 2026-09-05: 68
- 2026-09-04: 67
- 2026-09-03: 67
- 2026-09-02: 66
- 2026-09-01: 66
- 2026-08-31: 65
- 2026-08-30: 65
- 2026-08-29: 64
- 2026-08-28: 64

## Common questions

### What is the LoopingAgent MCP server?

LoopingAgent is an MCP server listed in the public MCP registry as com.loopingagent/loopingagent-mcp. English blog + agentic AI architect profile (Paris): search, full text, projects, booking. This page covers its hosted endpoint (https://loopingagent.com/api/mcp).

### Is the LoopingAgent MCP server safe to use?

LoopingAgent scores 75 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the LoopingAgent MCP server expose?

LoopingAgent exposes 9 tools: get_profile, get_skill, list_articles, get_article, list_projects, and 4 more. Their descriptions and schemas cost roughly 775 tokens of context every time the server is loaded.

### Does the LoopingAgent MCP server require authentication?

No. We connected to LoopingAgent without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

### Is the LoopingAgent MCP server still maintained?

LoopingAgent is still listed as active in the MCP registry. We last reached this channel on 20 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

## Links

- Remote endpoint: https://loopingagent.com/api/mcp
- Repository: https://gitlab.com/laurentknauss/blog
- Website: https://loopingagent.com/
- Changelog RSS feed: https://verifymcp.io/servers/com-loopingagent-loopingagent-mcp/api-mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/com-loopingagent-loopingagent-mcp/api-mcp.json
- HTML version of this page: https://verifymcp.io/servers/com-loopingagent-loopingagent-mcp/api-mcp