# LynxPrompt (oci · drumsergio/lynxprompt-mcp)

Search, read and manage AI agent instruction blueprints (AGENTS.md, CLAUDE.md) on LynxPrompt

- Trust score: 44/100 (low)
- Change this week: +4
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-05

## Components

- npm · `lynxprompt-mcp`: 48/100, [markdown](https://verifymcp.io/servers/geiserx-lynxprompt-mcp/lynxprompt-mcp.md), [page](https://verifymcp.io/servers/geiserx-lynxprompt-mcp/lynxprompt-mcp)
- oci · `drumsergio/lynxprompt-mcp`: 44/100 (this document), [markdown](https://verifymcp.io/servers/geiserx-lynxprompt-mcp/drumsergio-lynxprompt-mcp.md), [page](https://verifymcp.io/servers/geiserx-lynxprompt-mcp/drumsergio-lynxprompt-mcp)

## Channel facts

- Registry: `oci`
- Package: `drumsergio/lynxprompt-mcp`
- Version: `v0.3.0`
- Transport: `stdio`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, 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 2026-11-05.

- **Supply Chain Security**: 0/100
  - No malware scan is available for this kind of package: the supply-chain vendors we use do not cover it. This is a permanent gap in our coverage, not a finding about the package.
  - Known CVEs could not be checked: this artifact ships no SBOM or dependency manifest, so there is no dependency list to read.
  - Install-script risk not yet assessed.
  - Dependency health could not be checked: this artifact ships no SBOM or dependency manifest, so there is no dependency list to read.
- **Provenance & Transparency**: 35/100
  - Source repository is publicly reachable at the declared URL.
  - Provenance check failed: no build-provenance attestation is published.
  - License check failed: no license is declared.
  - Actively maintained (last published 6 days ago).
  - Publishes a security disclosure policy (SECURITY.md).
- **Schema Quality & AI Usability**: 80/100
  - 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 2074 tokens (~159/item across 13 items; 10 tools + 3 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 30/100
  - Stability observed for 9 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.
  - Structured output schemas are declared (100% of tools); any adoption earns full credit.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - All 2 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation.
  - An AI judge read all 12 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a current MCP spec version (2026-07-28).

**Unverified: 1 category.** A category scored 0 because we could not verify it: a data source with nothing on this package, evidence we could not reach, or a check we could not run. We only credit what we can confirm.

## Install

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

LynxPrompt runs locally as a container image, launched with docker run --rm -i -e LYNXPROMPT_TOKEN -e LYNXPROMPT_URL -e LYNXPROMPT_READ_ONLY drumsergio/lynxprompt-mcp:v0.3.0. Ready-made configuration for Claude, Cursor, VS Code, Codex and 3 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add geiserx-lynxprompt-mcp -- docker run --rm -i -e LYNXPROMPT_TOKEN -e LYNXPROMPT_URL -e LYNXPROMPT_READ_ONLY drumsergio/lynxprompt-mcp:v0.3.0
```

This image reads LYNXPROMPT_TOKEN, LYNXPROMPT_URL and LYNXPROMPT_READ_ONLY. Set them in your client's env block for this server; docker run -e passes each one through to the container.

### Cursor

```json
{
  "mcpServers": {
    "geiserx-lynxprompt-mcp": {
      "command": "docker",
      "args": [
        "run",
        "--rm",
        "-i",
        "-e",
        "LYNXPROMPT_TOKEN",
        "-e",
        "LYNXPROMPT_URL",
        "-e",
        "LYNXPROMPT_READ_ONLY",
        "drumsergio/lynxprompt-mcp:v0.3.0"
      ]
    }
  }
}
```

This image reads LYNXPROMPT_TOKEN, LYNXPROMPT_URL and LYNXPROMPT_READ_ONLY. Set them in your client's env block for this server; docker run -e passes each one through to the container.

### VS Code

```json
{
  "servers": {
    "geiserx-lynxprompt-mcp": {
      "command": "docker",
      "args": [
        "run",
        "--rm",
        "-i",
        "-e",
        "LYNXPROMPT_TOKEN",
        "-e",
        "LYNXPROMPT_URL",
        "-e",
        "LYNXPROMPT_READ_ONLY",
        "drumsergio/lynxprompt-mcp:v0.3.0"
      ]
    }
  }
}
```

This image reads LYNXPROMPT_TOKEN, LYNXPROMPT_URL and LYNXPROMPT_READ_ONLY. Set them in your client's env block for this server; docker run -e passes each one through to the container.

### Codex

```bash
codex mcp add geiserx-lynxprompt-mcp -- docker run --rm -i -e LYNXPROMPT_TOKEN -e LYNXPROMPT_URL -e LYNXPROMPT_READ_ONLY drumsergio/lynxprompt-mcp:v0.3.0
```

This image reads LYNXPROMPT_TOKEN, LYNXPROMPT_URL and LYNXPROMPT_READ_ONLY. Set them in your client's env block for this server; docker run -e passes each one through to the container.

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "geiserx-lynxprompt-mcp": {
      "type": "local",
      "command": [
        "docker",
        "run",
        "--rm",
        "-i",
        "-e",
        "LYNXPROMPT_TOKEN",
        "-e",
        "LYNXPROMPT_URL",
        "-e",
        "LYNXPROMPT_READ_ONLY",
        "drumsergio/lynxprompt-mcp:v0.3.0"
      ],
      "enabled": true
    }
  }
}
```

This image reads LYNXPROMPT_TOKEN, LYNXPROMPT_URL and LYNXPROMPT_READ_ONLY. Set them in your client's env block for this server; docker run -e passes each one through to the container.

### Hermes

```yaml
mcp_servers:
  geiserx-lynxprompt-mcp:
    command: "docker"
    args: ["run", "--rm", "-i", "-e", "LYNXPROMPT_TOKEN", "-e", "LYNXPROMPT_URL", "-e", "LYNXPROMPT_READ_ONLY", "drumsergio/lynxprompt-mcp:v0.3.0"]
```

This image reads LYNXPROMPT_TOKEN, LYNXPROMPT_URL and LYNXPROMPT_READ_ONLY. Set them in your client's env block for this server; docker run -e passes each one through to the container.

### Netclaw

```json
{
  "McpServers": {
    "geiserx-lynxprompt-mcp": {
      "Transport": "stdio",
      "Command": "docker",
      "Arguments": [
        "run",
        "--rm",
        "-i",
        "-e",
        "LYNXPROMPT_TOKEN",
        "-e",
        "LYNXPROMPT_URL",
        "-e",
        "LYNXPROMPT_READ_ONLY",
        "drumsergio/lynxprompt-mcp:v0.3.0"
      ]
    }
  }
}
```

This image reads LYNXPROMPT_TOKEN, LYNXPROMPT_URL and LYNXPROMPT_READ_ONLY. Set them in your client's env block for this server; docker run -e passes each one through to the container.

### Other

```json
{
  "mcpServers": {
    "geiserx-lynxprompt-mcp": {
      "command": "docker",
      "args": [
        "run",
        "--rm",
        "-i",
        "-e",
        "LYNXPROMPT_TOKEN",
        "-e",
        "LYNXPROMPT_URL",
        "-e",
        "LYNXPROMPT_READ_ONLY",
        "drumsergio/lynxprompt-mcp:v0.3.0"
      ]
    }
  }
}
```

This image reads LYNXPROMPT_TOKEN, LYNXPROMPT_URL and LYNXPROMPT_READ_ONLY. Set them in your client's env block for this server; docker run -e passes each one through to the container.

## 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.

### 2026-11-05 (score 44, +1)

No change was recorded against any check on this day. Stability & Change Management went from 27 to 30. That category is still filling its 30-day observation window: 8 days of observed history at the previous scan, 9 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-03 (score 43, +1)

No change was recorded against any check on this day. Stability & Change Management went from 20 to 23. That category is still filling its 30-day observation window: 6 days of observed history at the previous scan, 7 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-01 (score 42, +1)

No change was recorded against any check on this day. Stability & Change Management went from 13 to 17. That category is still filling its 30-day observation window: 4 days of observed history at the previous scan, 5 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-31 (score 41, 0)

- [security regression] Provenance: unverified → fail

### 2026-10-30 (score 41, +1)

- [security regression] Provenance: fail → unverified

### 2026-10-29 (score 40, 0)

- [security regression] Stability: 0.03 → unverified
- [security regression] Tool safety: pass → unverified
- [functional regression] Schema quality: 142 → 159
- [functional regression] Capabilities: pass → unverified
- [functional regression] Tool coverage: 100 → unverified
- [functional regression] Schema quality: 100 → unverified
- [functional] Package version: v0.2.1 → v0.3.0

### 2026-10-28 (score 40, 0)

- [security regression] Stability: 0.00 → unverified
- [security regression] Tool safety: pass → unverified
- [security regression] Provenance: fail → unverified
- [functional regression] Capabilities: pass → unverified
- [functional regression] Tool coverage: 100 → unverified
- [functional regression] Schema quality: 100 → unverified
- [functional] Package version: v0.2.0 → v0.2.1

### 2026-10-27 (score 40, +33)

- [security improvement] Injection markers: unverified → pass
- [security] First check of Judged manipulation: pass
- [security] Stability: Stability not yet verified: not enough scan history yet (needs a 30-day window).
- [functional improvement] Stability: unverified → 0.00
- [functional improvement] Schema quality: unverified → 100
- [functional improvement] MCP protocol: unverified → pass
- [functional improvement] Tool coverage: unverified → 100
- [functional] First check of Schema quality: fail
- [functional] First check of Tool coverage: 100
- [functional] First check of Tool coverage: 100
- [functional] First check of Destructive annotations: 100
- [functional] First check of Schema quality: fail
- [functional] First check of Schema quality: excellent
- [functional] Package version: v0.1.2 → v0.2.0

## MCP tools (10)

### `create_blueprint` (~473 tokens)

Create blueprint

Save a new blueprint (an AI agent instruction file such as AGENTS.md or CLAUDE.md) to the token user's LynxPrompt account. Each call creates a new blueprint, even with the same name; to change an existing one use update_blueprint. Private by default; visibility PUBLIC publishes it to the public marketplace. To place it in a monorepo hierarchy pass hierarchy_id and repository_path. Returns the new blueprint with its bp_ id.

Input parameters:

- `category` (string): Category slug, e.g. web, devops, saas, mobile, data or other.
- `content` (string, required): The full text of the instruction file, at least 10 characters.
- `description` (string): One or two sentences on what the blueprint is for.
- `hierarchy_id` (string): Hierarchy to add the blueprint to (ha_..., from list_hierarchies or create_hierarchy).
- `name` (string, required): Blueprint name, at least 3 characters, e.g. "Next.js app AGENTS.md".
- `parent_id` (string): Parent blueprint inside the hierarchy (bp_...), e.g. the root AGENTS.md of the repo.
- `repository_path` (string): Where the file lives in the repository, relative to its root, e.g. packages/api/AGENTS.md.
- `tags` (array): Up to 10 tags of at most 30 characters, e.g. ["react", "typescript"].
- `team_id` (string): Team to share a TEAM blueprint with; send it together with visibility TEAM. Needed only when you belong to more than one team; with one team, that team is used.
- `type` (string): File format the blueprint is for. AGENTS_MD is AGENTS.md, CLAUDE_MD is CLAUDE.md, CURSOR_MDC a .cursor/rules/*.mdc file, *_COMMAND a slash command, AGENT_SKILL a skill's SKILL.md, AGENT_DEFINITION a…
- `visibility` (string): PRIVATE (only you), TEAM (your team) or PUBLIC. PUBLIC publishes the content to the public marketplace where anyone can read it.

Output parameters:

- `blueprint` (object)
- `success` (boolean)

### `create_hierarchy` (~145 tokens)

Create hierarchy

Create a hierarchy: a group that ties the blueprints of one repository together, for example every AGENTS.md of a monorepo. repository_root identifies the repository; if you already have a hierarchy with that repository_root, it is returned unchanged instead of a duplicate. Add blueprints to it with create_blueprint (hierarchy_id plus repository_path). Returns the hierarchy with its ha_ id.

Input parameters:

- `description` (string): Short description of the hierarchy.
- `name` (string, required): Display name, e.g. "acme monorepo".
- `repository_root` (string, required): Unique identifier of the repository, e.g. github.com/acme/monorepo.

Output parameters:

- `blueprints` (array): Every blueprint in the hierarchy, flat
- `hierarchy` (object)
- `message` (string)
- `success` (boolean)
- `total_blueprints` (integer)
- `tree` (array): The same blueprints nested by parent_id

### `delete_blueprint` (~54 tokens)

Delete blueprint

Permanently delete one of your blueprints. It cannot be restored. Confirm the id with get_blueprint or list_blueprints first.

Input parameters:

- `id` (string, required): Blueprint id, e.g. bp_clx1abc.

Output parameters:

- `message` (string)
- `success` (boolean)

### `delete_hierarchy` (~59 tokens)

Delete hierarchy

Permanently delete one of your hierarchies. The blueprints in it are not deleted: they stay in your account, unlinked from any hierarchy.

Input parameters:

- `id` (string, required): Hierarchy id, e.g. ha_clx1abc.

Output parameters:

- `message` (string)
- `success` (boolean)

### `get_blueprint` (~122 tokens)

Get blueprint

Read one blueprint the token can see, including its full content and its content_checksum: your own, your team's, or a public one found with search_blueprints. Call it before update_blueprint and pass content_checksum as expected_checksum, so an edit made elsewhere in the meantime is not overwritten. Only the owner can update or delete a blueprint. For a public blueprint of someone outside your team, repository_path is only the file name.

Input parameters:

- `id` (string, required): Blueprint id from list_blueprints or search_blueprints, e.g. bp_clx1abc.

Output parameters:

- `blueprint` (object)
- `success` (boolean)

### `get_hierarchy` (~85 tokens)

Get my hierarchy

Read one of your hierarchies with every blueprint in it, both as a flat list (blueprints[], with repository_path and content_checksum) and as a tree nested by parent_id. Blueprint content is not included; use get_blueprint for that.

Input parameters:

- `id` (string, required): Hierarchy id from list_hierarchies, e.g. ha_clx1abc.

Output parameters:

- `blueprints` (array): Every blueprint in the hierarchy, flat
- `hierarchy` (object)
- `message` (string)
- `success` (boolean)
- `total_blueprints` (integer)
- `tree` (array): The same blueprints nested by parent_id

### `list_blueprints` (~128 tokens)

List my blueprints

List the blueprints owned by the user of LYNXPROMPT_TOKEN, newest change first, without their content. Use it to find a blueprint id (bp_...) for get_blueprint, update_blueprint or delete_blueprint. Paged: when has_more is true, call again with offset increased by limit.

Input parameters:

- `limit` (integer): Blueprints per page, 1 to 100. Default 50.
- `offset` (integer): How many blueprints to skip. Default 0.
- `visibility` (string): Only blueprints with this visibility. Default all.

Output parameters:

- `blueprints` (array)
- `has_more` (boolean): True when another page exists: call again with offset + limit
- `limit` (integer)
- `offset` (integer)
- `total` (integer): Items matching, across all pages

### `list_hierarchies` (~107 tokens)

List my hierarchies

List your hierarchies. A hierarchy groups the blueprints of one repository (for example the AGENTS.md files of a monorepo) under one repository_root. Returns ids (ha_...) for get_hierarchy and delete_hierarchy. Paged like list_blueprints.

Input parameters:

- `limit` (integer): Hierarchies per page, 1 to 100. Default 50.
- `offset` (integer): How many hierarchies to skip. Default 0.

Output parameters:

- `has_more` (boolean): True when another page exists: call again with offset + limit
- `hierarchies` (array)
- `limit` (integer)
- `offset` (integer)
- `total` (integer): Items matching, across all pages

### `search_blueprints` (~263 tokens)

Search marketplace blueprints

Search the public LynxPrompt marketplace of AI agent instruction files (AGENTS.md, CLAUDE.md, Cursor rules, slash commands and so on). Use it to find blueprints other people published; get_blueprint reads a result's content. To find your own blueprints use list_blueprints instead. Needs no token. Returns one page of results (templates[] with id, name, description, author, type, tags) plus total and hasMore.

Input parameters:

- `category` (string): Category slug, e.g. web, devops, saas, mobile, data or other.
- `limit` (integer): Results per page, 1 to 50. Default 12.
- `page` (integer): Page number, starting at 1. Default 1.
- `query` (string): Words to match in name, description or tags, e.g. "nextjs". Leave out to list the most popular blueprints.
- `sort` (string): Result order. Default popular.
- `tags` (array): Match blueprints carrying any of these tags, e.g. ["react", "typescript"].
- `type` (string): "configs" for instruction files, "commands" for slash commands and workflows. Leave out for both.

Output parameters:

- `hasMore` (boolean): True when another page exists: call again with page + 1
- `popularTags` (array)
- `templates` (array)
- `total` (integer)

### `update_blueprint` (~397 tokens)

Update blueprint

Change one of your blueprints. Only the fields you pass change; content replaces the whole text and the old text is not kept. Read the blueprint with get_blueprint first and pass its content_checksum as expected_checksum: if someone edited it since (web UI, CLI, another agent) the call fails with 409 instead of overwriting their change. Setting visibility PUBLIC publishes it to the marketplace.

Input parameters:

- `category` (string): Category slug, e.g. web, devops, saas, mobile, data or other.
- `content` (string): New full text; replaces the current content.
- `description` (string): One or two sentences on what the blueprint is for.
- `expected_checksum` (string): content_checksum from get_blueprint. Strongly recommended whenever content changes.
- `id` (string, required): Blueprint id, e.g. bp_clx1abc.
- `name` (string): New name, at least 3 characters.
- `tags` (array): Up to 10 tags of at most 30 characters, e.g. ["react", "typescript"].
- `team_id` (string): Team to share a TEAM blueprint with; send it together with visibility TEAM. Needed only when you belong to more than one team; with one team, that team is used.
- `type` (string): File format the blueprint is for. AGENTS_MD is AGENTS.md, CLAUDE_MD is CLAUDE.md, CURSOR_MDC a .cursor/rules/*.mdc file, *_COMMAND a slash command, AGENT_SKILL a skill's SKILL.md, AGENT_DEFINITION a…
- `visibility` (string): PRIVATE (only you), TEAM (your team) or PUBLIC. PUBLIC publishes the content to the public marketplace where anyone can read it.

Output parameters:

- `blueprint` (object)
- `success` (boolean)

## Diagnostics

Captured diagnostic sections: Provenance. The full working is on the page: https://verifymcp.io/servers/geiserx-lynxprompt-mcp/drumsergio-lynxprompt-mcp#diagnostics

## Score history

- 2026-11-05: 44
- 2026-11-04: 43
- 2026-11-03: 43
- 2026-11-02: 42
- 2026-11-01: 42
- 2026-10-31: 41
- 2026-10-30: 41
- 2026-10-29: 40
- 2026-10-28: 40
- 2026-10-27: 40
- 2026-10-26: 7
- 2026-10-25: 7
- 2026-10-24: 7
- 2026-10-23: 7
- 2026-10-22: 6
- 2026-10-21: 7
- 2026-10-20: 7
- 2026-10-19: 7
- 2026-10-18: 7
- 2026-10-17: 7
- 2026-10-16: 7
- 2026-10-15: 7
- 2026-10-14: 7
- 2026-10-13: 7
- 2026-10-12: 7
- 2026-10-10: 7
- 2026-10-06: 7

## Common questions

### What is the LynxPrompt MCP server?

LynxPrompt is an MCP server listed in the public MCP registry as io.github.GeiserX/lynxprompt-mcp. Search, read and manage AI agent instruction blueprints (AGENTS.md, CLAUDE.md) on LynxPrompt. This page covers its container image (drumsergio/lynxprompt-mcp).

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

LynxPrompt scores 44 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 LynxPrompt MCP server expose?

LynxPrompt exposes 10 tools: create_blueprint, create_hierarchy, delete_blueprint, delete_hierarchy, get_blueprint, and 5 more. Their descriptions and schemas cost roughly 1,833 tokens of context every time the server is loaded.

### Is the LynxPrompt MCP server still maintained?

LynxPrompt is still listed as active in the MCP registry. We last reached this channel on 5 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

## Links

- Docker Hub: https://hub.docker.com/r/drumsergio/lynxprompt-mcp
- Repository: https://github.com/GeiserX/lynxprompt-mcp
- Changelog RSS feed: https://verifymcp.io/servers/geiserx-lynxprompt-mcp/drumsergio-lynxprompt-mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/geiserx-lynxprompt-mcp/drumsergio-lynxprompt-mcp.json
- HTML version of this page: https://verifymcp.io/servers/geiserx-lynxprompt-mcp/drumsergio-lynxprompt-mcp