Mind Polling

● Active

com.mindpolling/mindpolling

Polls of AI models: read public results with no key; create and run your own with an API key.

Connect this server

One click to install, or copy the config below. Suits: Claude Desktop · Cursor.

Add to Cursor Add to VS CodeClaude Desktop / Claude Code: paste the config below.

Or add it manually — claude_desktop_config.json (Claude Desktop) or .cursor/mcp.json (Cursor):

{
  "mcpServers": {
    "mindpolling": {
      "command": "npx",
      "args": [
        "-y",
        "mindpolling@1.0.0",
        "mcp"
      ],
      "env": {
        "MIND_POLLING_API_KEY": "<your MIND_POLLING_API_KEY>"
      }
    }
  }
}
One line, from the terminal
Claude Code
claude mcp add --env MIND_POLLING_API_KEY='<your MIND_POLLING_API_KEY>' --transport stdio mindpolling -- npx -y mindpolling@1.0.0 mcp
OpenAI Codex CLI
codex mcp add mindpolling --env MIND_POLLING_API_KEY='<your MIND_POLLING_API_KEY>' -- npx -y mindpolling@1.0.0 mcp
VS Code
code --add-mcp '{"name":"mindpolling","type":"stdio","command":"npx","args":["-y","mindpolling@1.0.0","mcp"],"env":{"MIND_POLLING_API_KEY":"<your MIND_POLLING_API_KEY>"}}'

Syntax from each client's docs (Claude Code: claude mcp add; Codex: codex mcp add; VS Code: code --add-mcp). Placeholders in angle brackets are values you fill in.

Environment variables
  • MIND_POLLING_API_KEYsecretA Mind Polling API key, for your own polls. Without it: public polls.

A starting point — check the repository for exact arguments and setup. Restart your client after editing the config.

Category
Other
Version
1.0.0
Registry
active
Published
11/20/2026
Listed in:Official MCP registry ↗how this is checked

Is it safe? Is it maintained?

Serverdex check: Nov 22, 2026

Looks healthy: Mind Polling is maintained, open source, hosted endpoint answering without a key.

Maintained
Active
Last commit 2 days ago (Nov 19, 2026), 0 open issues.
Official registry
Active
Published as com.mindpolling/mindpolling in the official MCP registry, version 1.0.0.
Source
Open source, MIT-0
Public repository under the MIT-0 licence, 0 stars, 0 forks.
Runs
Local package or hosted
Ships as a local package (npm) that runs on your machine, and as a hosted endpoint at mindpolling.com that receives what your client sends it.
Credentials
None needed to connect
The hosted endpoint completed the Serverdex initialize + tools/list handshake with no key (checked Nov 22, 2026); individual tools may still ask for one.
Owner
Unclaimed
Nobody has claimed this page yet; the data above comes from the registry, GitHub and the live check.

Facts only: last commit and licence from GitHub, the entry's status from the official registry, credentials from the live check. Not a code audit — run the security scan on the endpoint yourself and see the status history.

Live check

checked Nov 22, 2026, 07:07 UTCStatus history & uptime →
● Working118 msprotocol 2025-06-18v1.0.0toolsresourcesprompts

The endpoint answered the MCP handshake as "Mind Polling" and listed 22 tools. Answering since Nov 21, 2026.

Context cost ≈ 11k tokens of tool definitions a client loads per conversation (estimate: characters ÷ 4) across 22 tools.

Tools (22)

  • Check a key: whose it is, the account's balance, the key's scopes, mode and monthly allowance with what it has committed this month, the rate limits, and every operation this key cannot call with the reason and the remedy. Call this first with a new key. (GET /api/v1/me)

  • list_polls10 params

    Every public poll, latest run first, filtered and sorted as the directory at /polls is: by topic (a topic's slug), status, model, lab and search, sorted by latest run, newest, most answers or ending soon. With a key that has the read scope, mine=true lists your own polls instead (a test key lists test polls only; the filters apply to public polls). Use updated_since to fetch only polls that changed, then get_results for each. (GET /api/v1/polls)

    Show parameters
    • minestringtrue: your own polls (needs a key with read). Default: public polls.
    • updated_sincestringOnly polls whose last run or edit is after this moment.
    • topicstringPublic polls: only those with this topic, by its slug (as in /polls/topics/{slug}).
    • statusstringPublic polls: running (on a schedule), stopped (ended, paused, or run once by hand), or all (the default).
    • sortstringPublic polls: latest run first (the default), newest published, most answers, or soonest end date (polls with none last).
    • modelstringPublic polls: only those asking this model, by its display name.
    • labstringPublic polls: only those asking a model from this lab, such as Anthropic.
    • qstringPublic polls: only those whose title, description, first question or topics contain every word given.
    • limitintegerItems per page, 1 to 100.
    • cursorstringnext_cursor from the previous page, unchanged.
  • get_poll1 param

    A poll's settings and every version: the questions and their wordings exactly as asked, the models, samples and search depth, plus any prediction markets associated with it. Accepts the poll's id or its public address (slug). (GET /api/v1/polls/{id})

    Show parameters
    • idstringrequiredThe poll's id, or its public address (slug).
  • get_results5 params

    A poll's results. For choice and scale questions each answer's share per model per run, for number and scale questions each model's mean, each with its 95% repeat range (low, high). Pooled over wordings, each wording counts once and the range combines each wording's own sampling error; the wording range (wording_low, wording_high) says how far the wordings' own figures lie apart and is never merged into it, and any_low and any_high give a range for any phrasing where 5 or more rephrasings were asked. Every point carries available_at, when this reader could first have seen it. as_of reads the results exactly as they stood at a past moment (no later run and no later re-reading of an answer), and first_release=true reads every answer as first published; both need a free key (the historical reads are what a backtest pulls, and a key says who is pulling). Versions are continued onto the latest unless version is given. (GET /api/v1/polls/{id}/results)

    Show parameters
    • idstringrequiredThe poll's id, or its public address (slug).
    • as_ofstringRead as things stood at this moment (RFC 3339): only runs this reader could have seen by then, each answer as it was read then. Needs a key.
    • first_releasestringtrue: each answer's first reading, as first published, rather than its latest. Needs a key.
    • versionintegerOne version only. Default: every version continued onto the latest.
    • viewstringpooled combines a question's wordings, each once; by-wording keeps them apart.
  • list_runs3 params

    A poll's runs, newest first: when each was due, started and finished, its status and counts, and available_at, when this reader could first have read it. A stranger sees only runs that have become available; the owner also sees queued and running ones, and charges. (GET /api/v1/polls/{id}/runs)

    Show parameters
    • idstringrequiredThe poll's id, or its public address (slug).
    • limitintegerItems per page, 1 to 100.
    • cursorstringnext_cursor from the previous page, unchanged.
  • list_calls5 params

    Every call behind one of your polls' results, oldest first: the prompt and system prompt exactly as sent, every setting, the raw reply, how it was read, which model answered, tokens and charges, and read_market (whether its search read a prediction market). Filter by run. as_of reads each answer as it was read then. Only the poll's owner reads its calls, public or not: a public poll's readers get its results (get_results), which quote a sample reply per question. (GET /api/v1/polls/{id}/calls)

    Show parameters
    • idstringrequiredThe poll's id, or its public address (slug).
    • run_idstringOnly this run's calls.
    • as_ofstringRead as things stood at this moment (RFC 3339): only runs this reader could have seen by then, each answer as it was read then.
    • limitintegerCalls per page, 1 to 500.
    • cursorstringnext_cursor from the previous page, unchanged.
  • Every model you can put in a poll's panel right now: its provider and id (what create_poll's panel takes), name, lab, the search depths it is offered at, a typical answer's charge, and its last 30 days of cut-off and error rates. A model is offered only after it has been measured. (GET /api/v1/models)

  • Up to five places from Google Places whose names match q: countries, states and provinces, counties, cities and ZIP or postal codes, never an address or a business. Each has an id and its text; read the one you want with get_place, and put the result in the wording's place. (GET /api/v1/places)

    Show parameters
    • qstringrequiredWhat to look for, such as Alaska or Bethel.
    • sessionstringOptional: one UUID you make for a search and the read that follows it, which Google bills as one session.
  • get_place2 params

    Read one place from Google Places by its id, in the shape a wording's place takes in create_poll and update_poll: its name, kind (country, region, county, city or postal_code) and ISO country and region codes. Any other place, such as an address or a business, is refused. Models never see a wording's place; it is there so results can be shown by place. (GET /api/v1/places/{id})

    Show parameters
    • idstringrequiredA Google place id, from search_places.
    • sessionstringOptional: one UUID you make for a search and the read that follows it, which Google bills as one session.
  • rotate_key

    Replace the secret of the key making this request, keeping its name, scopes, allowance and history. The new key is in the response, shown once; the old one stops working immediately. Use it when a key may have leaked. (POST /api/v1/me/key/rotate)

  • revoke_key

    Revoke the key making this request. It stops working at once and cannot be restored; polls it started stop at their next run. Use it when a key has leaked and you do not need a replacement. (DELETE /api/v1/me/key)

  • create_poll20 params

    Create a poll from a definition: questions and their wordings, the models to ask (provider and model from list_models), samples per cell, search depth, schedule and dates. It is saved as a draft and costs nothing; call estimate_poll for its cost, then start_poll or run_poll_now. A test key makes a test poll, which runs on a stub model and charges nothing. Send an Idempotency-Key so a retry cannot make two polls. (POST /api/v1/polls)

    Show parameters
    • titlestringrequiredThe poll's title.
    • descriptionstringWhat the poll is for, or empty.
    • index_namestringA name for the composite of the poll's Better-Worse index questions, such as "AI Economy Index"; empty for "Composite Better-Worse index". Shown only when two o
    • schedulestringrequiredonce, daily or weekly.
    • samples_per_cellintegerrequiredHow many times each model is asked each wording per run, 1 to 50: more samples, narrower ranges.
    • run_timeThe time of day it runs, HH:MM in time_zone; null runs from the moment it is started.
    • time_zonestringThe IANA time zone of its dates and run time.
    • run_weekdayWeekly polls: the day it runs, 0 = Sunday.
    • start_dateThe first day it runs, YYYY-MM-DD in time_zone; needs run_time.
    • end_dateThe last day it runs, at most 90 days after start_date.
    • sample_percentintegerThe share of the poll's wordings each scheduled run asks, 1 to 100 percent; every wording is asked once before any is asked again. Left out: unchanged (100 for
    • deliverystringrealtime (the default), or batch: scheduled runs ask the models that can be batched (Anthropic) through the providers' batch APIs, cheaper, with answers arrivin
    • mentionsarrayFree-text questions only: up to 6 names per question whose mention the results count, per model, as the share of answers that name each (and the share that name
    • tracked_domainsarrayUp to 5 sites (domains such as example.com; a scheme, path or www. is dropped). The results count, per model, how many answers that searched read or cited each,
    • search_depthintegerSearches allowed per answer, for every model with search on.
    • system_promptstringThe system prompt every wording is asked under unless it has its own; empty for none.
    • change_notestringWhy this version differs from the last, kept in the poll's history.
    • restored_fromThe earlier version this one was started from, or null.
    • questionsarrayrequired1 to 50 questions, in order.
    • panelarrayrequired1 to 30 models to ask, each once.
  • update_poll21 params

    Replace a poll's definition with a new one. Before its first run the version is edited in place; once a version has run it is locked and a new version is made, so results always say what was asked. Send the whole definition, as create_poll takes it. (PUT /api/v1/polls/{id})

    Show parameters
    • idstringrequiredThe poll's id, or its public address (slug).
    • titlestringrequiredThe poll's title.
    • descriptionstringWhat the poll is for, or empty.
    • index_namestringA name for the composite of the poll's Better-Worse index questions, such as "AI Economy Index"; empty for "Composite Better-Worse index". Shown only when two o
    • schedulestringrequiredonce, daily or weekly.
    • samples_per_cellintegerrequiredHow many times each model is asked each wording per run, 1 to 50: more samples, narrower ranges.
    • run_timeThe time of day it runs, HH:MM in time_zone; null runs from the moment it is started.
    • time_zonestringThe IANA time zone of its dates and run time.
    • run_weekdayWeekly polls: the day it runs, 0 = Sunday.
    • start_dateThe first day it runs, YYYY-MM-DD in time_zone; needs run_time.
    • end_dateThe last day it runs, at most 90 days after start_date.
    • sample_percentintegerThe share of the poll's wordings each scheduled run asks, 1 to 100 percent; every wording is asked once before any is asked again. Left out: unchanged (100 for
    • deliverystringrealtime (the default), or batch: scheduled runs ask the models that can be batched (Anthropic) through the providers' batch APIs, cheaper, with answers arrivin
    • mentionsarrayFree-text questions only: up to 6 names per question whose mention the results count, per model, as the share of answers that name each (and the share that name
    • tracked_domainsarrayUp to 5 sites (domains such as example.com; a scheme, path or www. is dropped). The results count, per model, how many answers that searched read or cited each,
    • search_depthintegerSearches allowed per answer, for every model with search on.
    • system_promptstringThe system prompt every wording is asked under unless it has its own; empty for none.
    • change_notestringWhy this version differs from the last, kept in the poll's history.
    • restored_fromThe earlier version this one was started from, or null.
    • questionsarrayrequired1 to 50 questions, in order.
    • panelarrayrequired1 to 30 models to ask, each once.
  • estimate_poll1 param

    What a poll will cost, from the same prices the worker charges by: one run's typical and 95th-percentile charge, what a run holds from the balance while it runs, and what starting the poll commits (hold per run times the runs left before its end date, or a month of runs when it has none). Show this to the account holder before start_poll or run_poll_now. (GET /api/v1/polls/{id}/estimate)

    Show parameters
    • idstringrequiredThe poll's id, or its public address (slug).
  • start_poll2 params

    Start a draft or paused poll on its schedule. Each run spends the account's balance, so the request must carry max_cost_usd, the most it may commit (estimate_poll gives the figure, and a refusal says the exact amount). Refused with 402 if the balance cannot cover it and 409 if this key's monthly allowance cannot; nothing is spent by a refusal. Confirm the cost with the account holder first. (POST /api/v1/polls/{id}/start)

    Show parameters
    • idstringrequiredThe poll's id, or its public address (slug).
    • max_cost_usdnumberThe most, in US dollars, you agree this may commit. Required: the call is refused with the amount it needs if this is missing or too low.
  • run_poll_now3 params

    Queue one run of a poll now, whatever its schedule. It asks every wording, or with share=true the next part of the poll's rotation at its sample_percent, exactly as a scheduled run would. It spends the account's balance, so the request must carry max_cost_usd (estimate_poll's run_now.hold_micro). Follow it with get_live_run, then read get_results once it settles. Refused with 409 if a run is already in progress. (POST /api/v1/polls/{id}/run)

    Show parameters
    • idstringrequiredThe poll's id, or its public address (slug).
    • max_cost_usdnumberThe most, in US dollars, you agree this may commit. Required: the call is refused with the amount it needs if this is missing or too low.
    • sharebooleantrue: ask the next part of the rotation at the poll's sample_percent, as a scheduled run would (estimate_poll's per_run). false: every wording (run_now).
  • pause_poll1 param

    Pause an active poll: no further runs start until it is started again. A run already in progress finishes. Needs only the write scope, since pausing stops spending. (POST /api/v1/polls/{id}/pause)

    Show parameters
    • idstringrequiredThe poll's id, or its public address (slug).
  • get_live_run1 param

    The run in progress, if any: how many answers are done of how many, each model's cells as they settle, and outcome counts; plus the poll's status, when it next runs, and the last run that settled. Poll this every few seconds while a run is active; when last_settled changes, read get_results. (GET /api/v1/polls/{id}/status)

    Show parameters
    • idstringrequiredThe poll's id, or its public address (slug).
  • list_changes5 params

    The change feed: every settled run, every poll made public or private, every new version and every revision of published answers, oldest first, after a cursor. Needs a free key with read: public polls' changes by default, and mine=true for your own polls'. Keep next_cursor and ask again later, adding a random minute so every client does not ask at once; or register a webhook to be told. (GET /api/v1/changes)

    Show parameters
    • minestringtrue: your own polls' changes (needs a key with read). Default: public polls'.
    • poll_idstringOnly this poll's changes.
    • typesstringComma-separated event types to include. Default: all.
    • limitintegerEvents per page, 1 to 500.
    • cursorstringnext_cursor from the previous page. Leave it out to start from the oldest kept event.
  • Register an https URL to receive events as Standard Webhooks: a POST with webhook-id, webhook-timestamp and webhook-signature (v1, HMAC-SHA256 of id.timestamp.body with the secret returned here, once). scope mine sends your own polls' events, public every public poll's; poll_id narrows it to one poll. Only events after it is made are sent. Answer 2xx to acknowledge; failures are retried for about three days, and 410 stops deliveries. (POST /api/v1/webhooks)

    Show parameters
    • urlstringrequiredYour receiver's https URL.
    • scopestringmine: your own polls. public: every public poll.
    • eventsarrayWhich event types to send. Default: all.
    • poll_idOnly this poll's events.
  • Your webhook endpoints with their scope, events and whether each is disabled, and why. A disabled endpoint receives nothing; delete it and make another once the receiver works. (GET /api/v1/webhooks)

  • Delete a webhook endpoint: nothing more is sent to it, including retries in progress. (DELETE /api/v1/webhooks/{id})

    Show parameters
    • idstringrequiredThe webhook's id.

Checked by Serverdex with a plain initialize + tools/list call to mindpolling.com/mcp, no credentials, about once a day. A failed check is never a removal.

On GitHub

read Nov 21, 2026
Stars
0
Forks
0
Last push
Nov 19, 2026
License
MIT-0

JavaScript

From the README

For developers: the API, the MCP server and keys Everything a person can do on Mind Polling, a program can do too, through a REST API and an MCP server that offer the same operations. Public polls need no key. Without a key, and with one • No key: find public polls and read their latest results, up to 120 requests a minute per address. • A key with the read scope: results as they stood at a past moment, the feed of changes, and your own polls. It is free and can spend nothing. • A key with write and run: create polls and run them. A run spends the account's prepaid balance, so every call that spends must say the most it may cost (maxcostusd), and is refused without it. A key is made by the account holder, on the API keys page, never by a program. How keys work covers scopes, spending limits and what is logged. The API • Base address: https://mindpolling.com/api/v1 • Description: OpenAPI 3.1, generated from the code that answers. • Guide: the API guide, every operation with what it needs. • Index: /api, the operations as JSON. Try it, with nothing to install: The guide opens with the whole API in five lines. The MCP server The same operations are tools at https://mindpolling.com/mcp (Streamable HTTP), named by their operation id. Add that address to an MCP client as a remote server. With no key it reads public polls; for your own, send a key as Authorization: Bearer.…

Read the full README on GitHub →

Remotes

  • streamable-httphttps://mindpolling.com/mcp

The most-starred Other servers in the index, with their live-check result.

ServerStarsLast pushLive check
Labelhead Artist Momentum114,594Nov 2026Working
World Monitor91,002Nov 2026Needs sign-in
Tldraw51,470Nov 2026Working
OpenSEO28,515Nov 2026Needs sign-in
Windows MCP11,833Nov 2026Local / not checked

Mind Polling: questions people ask

Is Mind Polling a remote or a local MCP server?
According to its entry in the official MCP registry, Mind Polling ships as a hosted endpoint (streamable-http) that your client connects to by URL and as a local package (npm) that your client starts on your machine. Use the hosted endpoint when your client supports Streamable HTTP; use the package when you want it to run locally.
Does Mind Polling need an API key?
Its hosted endpoint completed the Serverdex live check — an MCP initialize + tools/list call — with no credentials on Nov 22, 2026. Individual tools may still ask for a key when called.
Is Mind Polling safe to use?
Looks healthy: Mind Polling is maintained, open source, hosted endpoint answering without a key. In detail — maintained: Active; official registry: Active; source: Open source, MIT-0; runs: Local package or hosted; credentials: None needed to connect. Serverdex check of Nov 22, 2026. This is a reading of the repository, the registry entry and the live check, not a code audit; run the Serverdex security scan on the endpoint before trusting it with real data.
Is Mind Polling still maintained?
Active: the repository's last commit 2 days ago. Last push Nov 19, 2026, 0 GitHub stars, MIT-0 licence. Read from GitHub on Nov 21, 2026.
What tools does Mind Polling expose?
22 tools as listed by the server itself during the live check, including get_me, list_polls, get_poll, get_results, list_runs. The full list with parameters is in the Live check section above.
How do I add Mind Polling to Claude, Cursor or VS Code?
Copy the config in "Connect this server" into your client's MCP config file (claude_desktop_config.json, ~/.cursor/mcp.json or .vscode/mcp.json), or use the one-click Add to Cursor / Add to VS Code buttons and the one-line commands for Claude Code and Codex; then restart the client.
Browse all Other →

Add the badge to your site

Show visitors that Mind Polling is listed here — it’s also the link we check for a free listing.

Mind Polling — listed on Serverdex

HTML — for your website

<a href="https://serverdex.io/server/com-mindpolling-mindpolling?utm_source=badge"><img src="https://serverdex.io/brand/badge.svg" alt="Mind Polling — listed on Serverdex" width="123" height="40" loading="lazy"></a>

Recommended. A dofollow link from your own domain is the one that counts for search engines, and it's the link we check for a free listing.

Markdown — for your README

[![Mind Polling — listed on Serverdex](https://serverdex.io/brand/badge.svg)](https://serverdex.io/server/com-mindpolling-mindpolling?utm_source=badge)

Nice for visibility, but GitHub marks README links nofollow, so it doesn't pass authority. Use the HTML badge on your site as well.

Add to CursorAdd to VS CodeOpen in Claude Code

Install buttons — for your README

[![Add to Cursor](https://serverdex.io/brand/install-cursor.svg)](https://serverdex.io/install/cursor/com-mindpolling-mindpolling) [![Add to VS Code](https://serverdex.io/brand/install-vscode.svg)](https://serverdex.io/install/vscode/com-mindpolling-mindpolling) [![Open in Claude Code](https://serverdex.io/brand/install-claude-code.svg)](https://serverdex.io/install/claude-code/com-mindpolling-mindpolling)

One click opens Cursor or VS Code with this server's config prefilled; the Claude Code button lands on the one-line command. The links point at Serverdex, so when your config changes the buttons keep working.

Install buttons — HTML for your docs

<a href="https://serverdex.io/install/cursor/com-mindpolling-mindpolling"><img src="https://serverdex.io/brand/install-cursor.svg" alt="Add to Cursor — via Serverdex" width="140" height="28"></a>
<a href="https://serverdex.io/install/vscode/com-mindpolling-mindpolling"><img src="https://serverdex.io/brand/install-vscode.svg" alt="Add to VS Code — via Serverdex" width="147" height="28"></a>
<a href="https://serverdex.io/install/claude-code/com-mindpolling-mindpolling"><img src="https://serverdex.io/brand/install-claude-code.svg" alt="Open in Claude Code — via Serverdex" width="180" height="28"></a>

Same buttons as plain links for a docs page or website.

Prefer a live badge with the score, stars and live check? Score badge (links to a page that explains the number and back to this listing).