Skip to content
ViewsMeet logo

ViewsMeet MCP server

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

read 2026-10-21

← Back to ViewsMeet

Whose server it is
  • Registry namecom.viewsmeet/participateverified in the MCP registry

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

When we asked itchecked 2026-10-21
  • Stateanswerschecked 2026-10-21
  • Tools14
  • Server calls itselfcom.viewsmeet/participate
  • Server version0.5.0
  • Protocol version2025-06-18

On 2026-10-21 the server answered initialize and tools/list without a sign-in. First answer in 49 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 2 of the 7 days it takes to judge reliability.

Once connected

  • create_friendship_score_relay change data without a sign-in: anyone with the address can call them.
  • Parameters are untyped or undescribed in 11 of 14 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: 2, the first on 2026-10-21
  • INITE MCP scoreafter a weeka score needs 7 daily checks: 2 so far
  • Answeredmeasuring2 of the 7 daily checks it takes to print a share
  • Median first answer225 ms
  • Space in an agent's context≈ 1,964 tokensthe definitions of all its tools (14), which an agent carries on every turn
  • Tool definitionsB · 87 of 100
  • Typed results14 of 14 toolsdeclared outputSchema: results come typed, read once
  • Parameters without a description: in 11 of 14

Worth a look

  • Tools that change data, on a server that answers without a sign-in: create_friendship_score_relay

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 offers14 tools · read 2026-10-21
  • get_daily_question_set

    Return today's public, curated either/or question set. No private challenge lookup.

  • request_ballot_challenge

    Issue one bounded challenge handle for a known pack, mode, and target. This does not enumerate challenges.

  • cast_ballot

    Submit enum-only self and prediction vectors for one issued challenge and nonce. Provenance is server-assigned.

  • get_ballot_receipt

    Retrieve one receipt by its exact opaque identifier. Receipt enumeration is not available.

  • get_cohort_results

    Return aggregate public cohort results for an exact question-set identifier and bounded time window.

  • get_connection_topology

    Return only the latest already-frozen public Connection Atlas DTO. Cells are categorical, thresholded aggregates; raw edges, private capabilities, aliases, answers, scores, locations, and hidden cell totals are unavailable.

  • get_methodology

    Return one curated methodology section selected from a fixed enum.

  • get_personality_instrument

    Return the exact versioned public-domain Mini-IPIP 20 instrument. No response vector is submitted or stored.

  • score_personality_responses

    Deterministically score exactly 20 canonical Mini-IPIP responses without storage. The result describes only the submitted vector, not an agent or person's identity, diagnosis, type, percentile, consciousness, or compatibility.

  • get_personality_perception_challenge

    Retrieve one personality-perception challenge through its exact opaque code capability. Challenge enumeration is unavailable. Prediction is an unvalidated perception game.

  • submit_personality_perception

    Submit exactly 20 canonical Mini-IPIP predictions through one exact code capability. Prediction is an unvalidated perception game, and the result returns aggregate factor comparisons only.

  • get_friendship_challenge

    Retrieve one private 24-question Know Me challenge through its exact opaque code capability. Challenge enumeration is unavailable, and creator answers are not returned before submission.

  • submit_friendship_prediction

    Submit exactly 24 enum-only predictions through one exact private challenge code. A separate publicTopologyOptIn boolean, off by default, may add only the participant relationship/software categories to the thresholded Connection Atlas…

  • create_friendship_score_relay

    Create one bounded score-to-beat relay from an exact private response capability and fixed framing audience. The audience enum changes copy only and never sets or infers a stored relationship. Use only after explicit operator…

How to connect

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

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

Add it

Claude Code, in a terminal

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

Add to CursorAdd to VS Code

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

OpenAPI spec

28 paths, read 2026-10-21. 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.