Skip to content
TCC Group logo

TCC Group MCP server

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

read 2026-11-02

← Back to TCC Group

Whose server it is
  • Registry namegroup.tcc/websiteverified in the MCP registry

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

When we asked itchecked 2026-11-02
  • Stateanswerschecked 2026-11-02
  • Tools18
  • Server calls itselfTCC MCP Server
  • Server version1.3.0
  • Protocol version2025-03-26

On 2026-11-02 the server answered initialize and tools/list without a sign-in. First answer in 820 ms.

Should an agent connect itNot proven either way yet
  • Whether its tools do the product's job has not been judged yet.
  • Checked on 1 of the 7 days it takes to judge reliability.

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: 1, the first on 2026-11-02
  • INITE MCP scoreafter a weeka score needs 7 daily checks: 1 so far
  • Answeredmeasuring1 of the 7 daily checks it takes to print a share
  • Median first answer827 ms
  • Space in an agent's context≈ 2,271 tokensthe definitions of all its tools (18), which an agent carries on every turn
  • Tool definitionsA · 100 of 100
  • Typed results5 of 18 toolsdeclared outputSchema: results come typed, read once
  • Every tool passes all six checks.

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 (25%), doing the product's job (25%), definitions (20%), context (10%), use (10%) and how readily a client connects (10%). 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 offers18 tools · read 2026-11-02
  • get_site_info

    Get site metadata and MCP server capabilities.

  • list_pages

    List published WordPress pages with pagination.

  • list_posts

    List published posts, insights, or case studies, optionally filtered by taxonomy.

  • list_taxonomy_terms

    List published taxonomy terms with counts.

  • search_content

    Search public pages, posts, insights, and case studies.

  • get_page_content_with_schema

    Get full page textual content and published JSON-LD schema for grounded evaluation.

  • search_enriched_page_contexts

    Search site content and return top matching page contexts enriched with full text and JSON-LD schema.

  • get_citation_links

    Return clean source links and markdown citation bullets for a query context.

  • get_schema_context

    Return the sitewide Organization schema context.

  • get_navigation

    Return the primary navigation structure.

  • get_team_directory

    Get the published, featured team member directory (Core-managed People profiles). Read-only and published-only, like every other tool.

  • get_person_profile

    Get one published team member profile and its schema.org Person JSON-LD by slug.

  • search_media_assets

    Search public, active Core-managed Media Assets eligible for this website and return safe delivery variants plus schema.org MediaObject JSON-LD. Private and management records are never returned.

  • search_documents

    Search the public documents (PDF files) that this website publishes and return each as a document card with its schema.org node. Filter by topic or sector (slugs), by the address of a page on this website to find the documents related to…

  • get_document

    Get one public document card, with its schema.org node, by the id that search_documents returns. A document that does not exist or is not published for this website returns the same not-found answer.

  • get_contact_options

    Get how a person can contact this organisation: the address of its contact page, the enquiry routes that page offers, and the email address, telephone number and office hours the site publishes. Use it when a person asks how to get in…

  • get_document_carousel

    Use this when a person wants to see documents that search_documents or get_document returned: it shows up to three of them as a carousel of cards, each with the document's title, summary, size, number of pages and preview image, a button…

  • get_contact_card

    Use this when a person asks how to get in touch with this organisation and would like to see it as a card: it shows the same facts as get_contact_options, which are the address of its contact page, the enquiry routes that page offers, and…

How to connect

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

{
  "mcpServers": {
    "website": {
      "type": "http",
      "url": "https://tcc.group/wp-json/tcc-mcp/v1/mcp"
    }
  }
}

Add it

Claude Code, in a terminal

claude mcp add --transport http tcc https://tcc.group/wp-json/tcc-mcp/v1/mcp

Add to CursorAdd to VS Code

claude.ai, ChatGPT and other clients: add https://tcc.group/wp-json/tcc-mcp/v1/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.