MCP server · DimensionKit
DimensionKit MCP Server
One-click install for Cursor, VS Code, Claude, and 20+ other MCP clients, powered by API Commons MCP Install — visit install.apicommons.org for more information.
Endpoint
Hosted endpoint · transport
Connect
This is a remote MCP server — point an MCP client at the endpoint URL. Clients with native remote support (Claude, Cursor, VS Code, …):
# mcp client config (e.g. .mcp.json / mcp settings)
{
"mcpServers": {
"dimensionkit-com": {
"url": "https://app.dimensionkit.com/mcp"
}
}
}
For stdio-only clients (older Claude Desktop, etc.), bridge with mcp-remote:
# Add to claude_desktop_config.json
{
"mcpServers": {
"dimensionkit-com": {
"command": "npx",
"args": ["-y", "mcp-remote", "https://app.dimensionkit.com/mcp"]
}
}
}
If the server requires authentication, add the provider's token/header (e.g. an X-API-Key) per its docs. A quick reachability check:
curl -i -X POST https://app.dimensionkit.com/mcp \
-H "Content-Type: application/json" -H "Accept: application/json, text/event-stream" \
-d '{"jsonrpc":"2.0","id":1,"method":"tools/list"}'
Tools
scorecard_design_guide— Read this before building or substantially editing a scorecard. It covers what to ask the user before starting, how to write questions nobody can game, how to write tier insights worth reading, and how to choose between the visual themes. Ask for a single topic when you only need one — “themes” for the look, “questions” for phrasing.list_scorecards— List the scorecards on this account, with their slug, publication status, how many people have submitted, and where each one is allowed to be embedded. Use the slug from this list to address any other tool.get_scorecard— Read one scorecard in full: its presentation/configuration, dimensions, questions, answer options, and tier bands. Use this before editing or to copy supported configuration into another scorecard.create_scorecard— Create a new draft with optional presentation, branding, scoring-tier, embed, legal, and email-capture configuration. Omitted settings keep sensible defaults. Content starts empty: add each dimension with add_dimension, its questions in one add_questions call, then its bands with set_dimension_tiers, then check_scorecard and publish_scorecard. Read scorecard_design_guide first if you have not.update_scorecard_config— Patch an existing draft or published scorecard without changing its dimensions, questions, answers, dimension tiers, or submissions. Omitted fields remain unchanged. privacyPolicyUrl, termsUrl, and branding.logo accept null to clear them. A newSlug rename does not create a redirect: the former public URL stops resolving. embed.addOrigin appends one origin and keeps the rest; embed.allowedOrigins replaces the list. The result is a summary — call get_scorecard for the full document.add_dimension— Add a scoring dimension to a scorecard. Each dimension is scored independently and gets its own tier bands. Create the dimension first, then add its questions.add_questions— Add every question for one dimension in a single call. This is the normal way to build a dimension; add_question exists for adding one to a dimension already built. By default a question is scored: answers must be distinct options ordered from worst to best, and four options is the house style. Tier bands are recalculated automatically, so never set them by hand after this. Set a question’s type to “open” for a free-text question instead — it takes no answers and is excluded from scoring.add_question— Add a question to a dimension. By default a question is scored: answers must be distinct options ordered from worst to best, and four options is the house style. Tier bands for the dimension are recalculated automatically, so never set them by hand after this. Set type to “open” for a free-text question instead — it takes no answers, is excluded from scoring, and the respondent’s own words are stored with the submission.set_dimension_tiers— Set the result bands for a dimension: a label and an insight for each, ordered from the weakest band to the strongest. Score ranges are derived from the dimension’s questions and are calculated for you — do not supply them.update_dimension— Change a dimension’s label, short label, weight, or position in the scorecard. Only the fields you send are changed. The dimension key cannot be changed - it is what its questions and recorded scores are filed under. Use set_dimension_tiers for tier labels and insights.update_question— Change a question’s wording, type, whether it’s required, answer options, or its position within its dimension. Only the fields you send are changed. Safe on a published scorecard: submissions already recorded keep the wording and scores they were given. A question id cannot be changed - remove and re-add if you need a different one.remove_question— Delete a question from its dimension. The dimension’s tier bands are recalculated, since removing a question lowers the highest score anyone can reach. Submissions already recorded keep the answers they gave to it.remove_dimension— Delete a dimension and every question in it. This is the widest destructive edit available - confirm the dimension key with get_scorecard first. Submissions already recorded keep the answers and scores they were given.check_scorecard— Report whether a scorecard is ready to publish, and what is weak about it, without changing the scorecard; a usage event is recorded. Problems block publication; warnings do not, but each one is something a respondent would notice. Run this before publish_scorecard rather than discovering problems through a failed publish.publish_scorecard— Make a scorecard publicly reachable, or take it back to draft. Publishing runs the full validity check: every dimension needs at least one question and a complete set of tier bands, so this is the step that tells you what is still missing.list_submissions— List people who have filled in your scorecards, newest first, with their overall result and per-dimension scores. Filter by scorecard, completion status, result tier, date, or a search over name, email, and company. Returns a breakdown of the matching set alongside the rows, so this answers “how are people scoring” as well as “who submitted”.get_submission— Read one submission in full: the contact details captured, the overall result, per-dimension scores, and the exact question-and-answer the person gave, grouped by dimension. Answers are the wording shown at the time they submitted, so this stays accurate even if the scorecard has been edited since. Also returns the recorded source origin/domain and all captured contact fields, including custom fields.
About MCP
The Model Context Protocol (MCP) is an open protocol Anthropic introduced for connecting LLM-based agents to external tools and data sources. Providers publish MCP servers that expose their API surface as structured, discoverable tools — an MCP-compatible client (Claude Desktop, Cursor, Cline, Continue, etc.) can connect to the server and call its tools without any per-provider integration code.
Browse every MCP server on the APIs.io network or compare with the broader Agent Skill surfaces of the same providers.
Work with this as data
Every MCP server here is available over the APIs.io API and to AI agents over MCP.