Skip to content
BeliefState logo

BeliefState MCP server

Which MCP servers are BeliefState'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 2026-10-27

← Back to BeliefState

Whose server it is
  • Registry nameai.beliefstate/investor-researchverified in the MCP registry

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

When we asked itchecked 2026-10-27
  • Stateanswerschecked 2026-10-27
  • Tools18
  • Server calls itselfBeliefState x402 research
  • Server version1.0.0
  • Protocol version2025-06-18

On 2026-10-27 the server answered initialize and tools/list without a sign-in. First answer in 1304 ms.

Should an agent connect itConnect it, with care
  • Its tools do check the sources and starting assumptions behind a call, but not compare a stock's hypothetical return against SPY.

Once connected

  • Parameters are untyped or undescribed in 17 of 18 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: 7, the first on 2026-10-27
  • INITE MCP score79 of 100answers 99 · does the job 50 · definitions 82 · context 73 · connects 100
  • What an agent can do with it1 of 2 use cases
  • Answered100% of days7 of 7 daily checks
  • Median first answer1112 ms
  • Space in an agent's context≈ 8,008 tokensthe definitions of all its tools (18), which an agent carries on every turn
  • Tool definitionsB · 82 of 100
  • Typed results16 of 18 toolsdeclared outputSchema: results come typed, read once
  • Parameters without a description: in 17 of 18
  • Not saying whether it only reads or can destroy: 2 of 18

What an agent can do with it

  • not sure · ask ticker questions in your AI and pull cited analyst records
  • cannot · compare a stock's hypothetical return against SPY
  • can do · check the sources and starting assumptions behind a call

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 offers18 tools · read 2026-10-27
  • get_belief_risks

    Read evidence-linked Risk objects for exactly one ticker, entity, Belief or explicit released corpus. Filter by person, source, publication dates, status or severity. Unknown assessments remain unknown; an empty high-severity filter does…

  • get_belief_catalysts

    Read evidence-linked Catalyst objects with qualified current status or explicit unknowns. Filter one ticker, entity, Belief or released corpus by person, source, publication dates or status. Current briefs include pending and unassessed…

  • get_author_track_record

    Read an investor's stored publication-based outcome cohorts over one explicit ticker, entity, Belief or released corpus scope and optional source/publication window. Includes losses, pending and ineligible counts, preserves…

  • search_beliefs

    Find investment ideas by thesis, topic or trade setup, with cited matching passages. Per-call x402 price: 1.50 USDC on Base.

  • get_belief

    Read a requested complete investment case or evidence beyond a brief, with risks, conditions and coverage gaps. An ordinary library overview can use get_brief without opening each case. Use paragraph_index only when it appears in the…

  • compare_beliefs

    Compare two cited investment cases for support, contradiction or dependency, including explicit unknown and unrelated outcomes. Optional comparison_focus selects a public research topic within both complete cases; the result applies to…

  • get_brief

    Use detail=current for a small typed view: up to three current Beliefs, each with up to three attached risks and three pending or unassessed catalysts, evidence URLs, timestamps, material qualifications and explicit unknowns. Open risks…

  • get_beliefs

    List dated investment ideas for a requested inventory or filtered research on one ticker or subject. Investor, direction and time filters are optional. An ordinary overview uses get_brief; listing the same research afterward is…

  • search_entities

    Find released companies, industries, themes and other research subjects by name or kind. Per-call x402 price: 0.02 USDC on Base.

  • get_belief_changes

    Read a mixed, ordered change journal: author-view revisions, distribution changes and calculated publication outcomes are separate domains with distinct clocks. Use belief_id for changes to one case and inspect each event's domain. Use…

  • get_context_assessment

    Open a dated engine context assessment and its permitted evidence. Engine analysis is separate from an investor's stated view. Per-call x402 price: 0.02 USDC on Base.

  • list_research_visuals

    List cited charts and tables for one investment case or context assessment. Per-call x402 price: 0.02 USDC on Base.

  • get_research_visual

    Read one cited chart or table, including its regions and paginated exact rows or data points. Per-call x402 price: 0.02 USDC on Base.

  • get_belief_relationships

    Inspect cited relationship paths within one investment case. Preserves stated links, engine inferences and unknowns. Per-call x402 price: 0.02 USDC on Base.

  • evaluate_belief_scenario

    Apply up to eight hypothetical condition assumptions to a case's recorded scenario model. Does not alter evidence or predict the investor's response. Per-call x402 price: 0.02 USDC on Base.

  • refresh_market_data

    Explicitly refresh missing or stale market data for one current company or subject, then return its research brief. Per-call x402 price: 0.02 USDC on Base.

  • get_tickers

    Free research coverage and company discovery.

  • search_companies

    Free research coverage and company discovery.

How to connect

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

{
  "mcpServers": {
    "investor-research": {
      "type": "http",
      "url": "https://beliefstate.ai/v1/research/mcp"
    }
  }
}

Add it

Claude Code, in a terminal

claude mcp add --transport http beliefstate https://beliefstate.ai/v1/research/mcp

Add to CursorAdd to VS Code

claude.ai, ChatGPT and other clients: add https://beliefstate.ai/v1/research/mcp as a custom connector in the settings.

OpenAPI spec

24 paths, read 2026-10-27. Open the spec ↗

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.