Skip to content
SecDim logo

SecDim MCP server

Which servers in the official MCP registry are SecDim's own, whether they answer, and what they offer. A program checked each of these, nobody copied them from a product page.

read 2026-10-19

← Back to SecDim

Whose server it is
  • Registry namecom.secdim/mcpverified in the MCP registry

The registry name sits under secdim.com. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.

When we asked itchecked 2026-10-19
  • Stateanswerschecked 2026-10-19
  • Tools7
  • Server calls itselfSecDim MCP
  • Server version1.27.2
  • Protocol version2025-06-18

On 2026-10-19 the server answered initialize and tools/list without a sign-in. First answer in 269 ms.

Should an agent connect itSkip it
  • Its tools do none of the product's use cases we checked: find and fix security flaws in sample repositories; practise exploiting prompt injection in LLM apps; check and secure code written by AI assistants.
  • Checked on 4 of the 7 days it takes to judge reliability.

Once connected

  • Parameters are untyped or undescribed in 7 of 7 tools: check arguments before calling.

Said by rules from the measurements above. The likely first call is a model's pick from the tool list; read its description before relying on it.

Measured dailydaily checks: 4, the first on 2026-10-19
  • INITE MCP scoreafter a weeka score needs 7 daily checks: 4 so far
  • What an agent can do with it0 of 3 use cases
  • Answeredmeasuring4 of the 7 daily checks it takes to print a share
  • Median first answer419 ms
  • Space in an agent's context≈ 2,295 tokensthe definitions of all its tools (7), which an agent carries on every turn
  • Tool definitionsC · 67 of 100
  • Typed results0 of 7 toolsdeclared outputSchema: results come typed, read once
  • Parameters without a description: in 7 of 7
  • Not saying whether it only reads or can destroy: 7 of 7

What an agent can do with it

  • cannot · find and fix security flaws in sample repositories
  • cannot · practise exploiting prompt injection in LLM apps
  • cannot · check and secure code written by AI assistants

Each of the product's use cases, put to Jev against this server's tool list: can an agent do it with these tools?

Worth a look

None of the five warning signs in these definitions.

A program checks the server once a day: initialize and tools/list, no model. Tokens are the definitions' length at about four characters a token. The grade averages six checks of every tool's name, description, schema and annotations; it says how well the tools are described, not whether they work. The score weighs what was measured and nothing else: answering (30%), doing the product's job (25%), definitions (20%), context (10%) and use (15%). A part that was not measured is left out, and a hidden instruction caps the score at 40. The state of vendors' MCP servers: method and numbers →

Tools it offers7 tools · read 2026-10-19
  • get_secdim_profile

    Fetch a SecDim player's profile: scores, completed challenges, skills, security interests and an experience estimate. Use this tool to understand a player's demonstrated secure coding ability before building a learning pathway. The…

  • search_play_challenges

    Return a list of hands-on SecDim Play secure coding challenges (labs) related to a detected or suspected vulnerability. SecDim Play challenges are scored, hands-on labs: find and fix a real vulnerability in running code to earn points and…

  • search

    Search for SecDim Play secure coding labs (hands-on, scored challenges). This tool searches across SecDim Play's hands-on secure coding labs based on the search query. The backend API handles parsing of vulnerability names, CWE IDs, and…

  • fetch

    Fetch detailed content for a specific SecDim Play lab (hands-on, scored challenge). Args: id: Lab ID in format "lab:slug" (e.g., "lab:xss-dom") Returns: Dictionary containing: - id: The lab ID - title: Lab title - content: Detailed…

  • search_learn_courses

    Search SecDim Learn courses. SecDim Learn provides tutorial-based courses (mixing video, text and hands-on lab topics) covering secure coding, secure design, vibe coding security, devsecops, and cloud security. Many courses are…

  • get_learn_course

    Get a SecDim Learn course's details, including its syllabus of topics. Args: course_slug: The course's slug, as returned by search_learn_courses (e.g. "owasp-top-10") Returns: Dictionary with the course's title, description, image, slug…

  • get_learn_topic

    Get a SecDim Learn topic's content. Args: course_slug: The course's slug, as returned by search_learn_courses (e.g. "owasp-top-10") topic_slug: The topic's slug, as returned by get_learn_course (e.g. "introduction-secure-coding") Returns…

How to connect

Add the server to your MCP client config. Claude Desktop, Cursor and most other clients read this shape:

{
  "mcpServers": {
    "secdim": {
      "type": "http",
      "url": "https://mcp.secdim.com/mcp"
    }
  }
}

Add it

Claude Code, in a terminal

claude mcp add --transport http secdim https://mcp.secdim.com/mcp

Add to CursorAdd to VS Code

claude.ai, ChatGPT and other clients: add https://mcp.secdim.com/mcp as a custom connector in the settings.

Each line is something a program found when it went looking: the registry entry, the server's own answer, a spec that parses. A missing line means we did not find it, not that it does not exist.