Skip to content
Stobox logo

Stobox MCP server

Which MCP servers are Stobox'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 2026-10-17

← Back to Stobox

Whose server it is
  • Registry nameio.stobox/intelligence-graphverified in the MCP registry

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

When we asked itchecked 2026-10-17
  • Stateanswerschecked 2026-10-17
  • Tools6
  • Server calls itselfstobox
  • Server version0.1.2
  • Protocol version2025-06-18

On 2026-10-17 the server answered initialize and tools/list without a sign-in. First answer in 106 ms.

Should an agent connect itSkip it
  • Its tools do none of the product's use cases we checked: score an asset against a twenty-five question readiness check; prepare offering documents for review by a licensed firm; issue a tokenized stake with transfer rules held on-chain.

Once connected

  • Parameters are untyped or undescribed in 4 of 6 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: 9, the first on 2026-10-19
  • INITE MCP score63 of 100answers 89 · does the job 0 · definitions 72 · context 100 · connects 100
  • What an agent can do with it0 of 3 use cases
  • Answered89% of days8 of 9 daily checks
  • Median first answer118 ms
  • Space in an agent's context≈ 846 tokensthe definitions of all its tools (6), which an agent carries on every turn
  • Tool definitionsC · 72 of 100
  • Typed results0 of 6 toolsdeclared outputSchema: results come typed, read once
  • Parameters without a description: in 4 of 6
  • Not saying whether it only reads or can destroy: 6 of 6

What an agent can do with it

  • cannot · score an asset against a twenty-five question readiness check
  • cannot · prepare offering documents for review by a licensed firm
  • cannot · issue a tokenized stake with transfer rules held on-chain

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 (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 offers6 tools · read 2026-10-17
  • stobox_knowledge_search

    Search Stobox's verified knowledge base on real-world-asset tokenization: canonical, source-linked answers, facts, and articles (GraphRAG: vector + relationship expansion). Use for any question about tokenization, RWA, security tokens…

  • stobox_term_lookup

    Explain one term, product, standard, or regulation from the Stobox knowledge graph — e.g. 'STBX', 'Compass', 'ERC-7943', 'MiCA'. Returns its authoritative description, aliases, relationships, and source documents.

  • stobox_related_topics

    Show what is connected to a term in the Stobox knowledge graph — the related products, standards, regulations, and concepts, 1–2 relationship hops out.

  • stobox_fact_check

    Verify a claim about Stobox or tokenization against the CANONICAL Stobox knowledge graph before repeating or publishing it. Returns a verdict (contradicted / supported / no_contradiction_detected / unverifiable), any canon violations with…

  • stobox_answer_context

    Build a source-linked briefing for answering a tokenization question: the top passages, entity facts, and source URLs in one prompt-ready block. Use it to ground an answer in verified Stobox knowledge before responding.

  • stobox_start_tokenization

    Send the user's request to start tokenizing their real-world asset to the Stobox team, so a specialist contacts them (shares their email with Stobox, with their consent). Call this ONLY when the user explicitly wants to BEGIN (not just…

How to connect

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

{
  "mcpServers": {
    "intelligence-graph": {
      "type": "http",
      "url": "https://mcp.stobox.io/mcp"
    }
  }
}

Add it

Claude Code, in a terminal

claude mcp add --transport http stobox https://mcp.stobox.io/mcp

Add to CursorAdd to VS Code

claude.ai, ChatGPT and other clients: add https://mcp.stobox.io/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.