MCP Analytics
A statistical analyst in your AI chat: bring data and a question, get a citable, re-runnable report.
Connector by mcpanalytics.aiOfficial · Domain verified by the MCP Registry
Install
Works with Claude Code, VS Code, Cursor, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install connector/mcpanalytics-ai-analytics
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Remote endpoint
https://api.mcpanalytics.ai/mcp/api-keyRemote (HTTP)
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: data-analysis, data-visualization
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this server can do and what it asks for, from its tool list and install config. Checked Oct 25, 2026.
- Tools
- 20 read · 6 write · 1 delete
- Secrets
- 1 (API keys, tokens or passwords)
- Install scripts
- Nothing to install (hosted)
- Runs as
- Hosted (remote endpoint)
Tools by what they do 27
From the running server's own tool list (tools/list) on Oct 25, 2026.
Read 20 · Look things up without changing anything.
aboutaccount_linkagent_advisorask_librarybuild_statuscheck_tool_fitdatasets_listdiscover_toolsfind_precedentmy_objectspackage_statuspath_answer
Show 8 more tools
path_resolverpath_reusereport_cardsreports_listreports_viewreview_estimatetools_schemawarehouse
Write 6 · Create, change, send or run things.
adjust_estimatedatasets_uploadpath_bespokepath_estimatepath_rerunpath_tool_run
Delete 1 · Delete, drop, revoke or wipe things.
schedules
Secrets and settings it asks for
Secrets: values you paste in that let it act as you.
X-API-Key
Network hosts it talks to 1
api.mcpanalytics.ai· found in remote endpoint, install command
Tools (27)
As the server listed them on Oct 25, 2026. Descriptions are the server’s own words; hidden characters are shown as [U+…].
aboutread-onlyPlatform documentation and info: how it works (Answer, Analytics, Custom Analytics), usage.
account_linkread-onlyDirect link to the right account page for anything not doable in chat: billing, browser upload, report management. Hand the user the link and guide them.
adjust_estimateApply the user's layout wishes to the estimate's page through the layout agent; a new named arrangement, nothing overwritten, no number changes.
agent_advisorread-onlyAI help desk: which analysis fits your question, interpreting results, fixing errors. Multi-turn.
ask_libraryread-onlyAsk a question across all your delivered analyses: a synthesized answer with citations back to specific reports.
build_statusread-onlyCheck a commissioned build in-chat: stage progress, queue position, rejection reason if the data didn't match the objective, honest ETA, report link when delivered.
check_tool_fitread-onlyBefore naming a library tool: does it fit THIS dataset for THIS question? Column mapping, missing required inputs, method-fit verdict, the places it delivers. Read-only.
datasets_listread-onlyList and search your uploaded datasets, with fuzzy matching on name, description, and tags. Returns each dataset's uuid:// reference for use in path_resolver and path_tool_run.
datasets_uploadGet your data in. Pass `data` as an array of row objects to create the dataset immediately and get a dataset_ref ready for path_resolver; omit it to get an upload link for a file only the user can reach. Add replace_ref (uuid://ID:KEY) with data to REFRESH an existing dataset in place; schedules and tools holding that reference read the new data on their next run.
discover_toolsread-onlyBrowse the analyses you can run: the ones you commissioned plus the platform Standard Library (prebuilt tools; each result tagged source:'own' or 'standard_library'). Plain-language match; no query lists everything, your own first. Nothing fits? Commission it with path_resolver.
find_precedentread-onlyBefore estimating: how did we answer this objective before, on this data or any data? Prior packages and library runs with their tools, mappings, bespoke module names, method and verdicts. Platform-wide, read-only.
my_objectsread-onlyList and search the objects you own across every question: the curated charts, tables and figures of each delivered package, grouped by objective.
package_statusread-onlyRead an analytics package back: status, every run under it, the report link once delivered.
path_answerread-onlyA read of the data (a total, an average, a count, the top group), computed on every row, in this response. When the question is not a read it says so and names the next step. Time: as path_resolver quotes.
path_bespokeOrder a custom analysis built for this data from a confirmed estimate, optionally with library tools alongside. Needs the person's yes and an idempotency key; a retry returns the first order. Time: as path_resolver quotes.
Show 12 more tools
path_estimateA rough answer over a sample and the layout of the full report, for the person to confirm before anything is ordered. Time: as path_resolver quotes.
path_rerunRun a delivered analysis again, on its own dataset or a new one: the same tools and mappings, no rebuild. Time: as path_resolver quotes.
path_resolverread-onlyWhich path a question about data should take (reuse, rerun, answer, tool_run, estimate, bespoke, ask or none), with the reason, every path's score and time, and the ready input for the path it picks. Executes nothing and charges nothing.
path_reuseread-onlyHand back the report already delivered for this question on this data. Time: as path_resolver quotes.
path_tool_runRun one or more tested library tools on this dataset, with charts and a written report. No custom build. Time: as path_resolver quotes.
report_cardsread-onlyBrowse a delivered report's individual cards (charts, tables, insights) inline in chat.
reports_listread-onlyYour report library: every analysis delivered, with status and links. Pass semantic_query to search report content in plain language.
reports_viewread-onlyGet a shareable browser link for a report, viewable without authentication.
review_estimateread-onlyThe estimate as you review it WITH the user: the question as understood, the estimated answer (sample, marked), every place and its question, the page link, a review checklist. Before path_bespoke.
schedulescan change or delete dataStanding re-runs of analyses you own: action='create' (weekly/monthly against a re-runnable data reference, connector:// or an https:// link; report emailed after each run), 'list', or 'cancel'.
tools_schemaread-onlyGet an analysis's parameter schema. ALWAYS call before path_tool_run.
warehouseread-onlyQuery your org's data warehouse free: browse the catalog (tables with column roles + computed metrics), semantically find data, plain-language ask, or named templates. Requires warehouse enablement (business plans).
Signals
- Stars
- 8
- Forks
- 1
- Open issues
- 4
- Last commit
- Oct 15, 2026 (13 days ago)
- Last release
- Oct 15, 2026 (14 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- Registry name
ai.mcpanalytics/analytics- Version
- 1.0.8
- Auth
- API key
- License
- MIT
- Repository
- github.com/embeddedlayers/mcp-analytics
- Website
- mcpanalytics.ai
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
Cite this page
MCP Analytics. Agent Mart. https://agentmart.dev/connectors/mcpanalytics-ai-analytics (last updated 2026-10-24)