MCP Analytics
Server Details
A statistical analyst in your AI chat: bring data and a question, get a citable, re-runnable report.
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- OAuth
- Works in Glama
- Last Tested
- Transport
- Streamable HTTP · MCP 2024-11-05
- URL
- Repository
- embeddedlayers/mcp-analytics
- GitHub Stars
- 9
- Server Listing
- MCP Analytics
- ChatGPT
- –
- Claude
- –
TDQS
Scored across 27 tools
Several clusters overlap heavily: path_resolver, discover_tools, find_precedent, check_tool_fit and agent_advisor all answer some version of "which analysis should I use," while path_estimate, review_estimate, adjust_estimate and path_bespoke form a four-tool estimate cluster that is easy to misselect. Reading artifacts is similarly spread across package_status, build_status, reports_list, report_cards and my_objects. The verbose descriptions do help draw boundaries (path_resolver explicitly executes nothing), but the naming alone leaves many ambiguous pairs.
Mostly snake_case, but the conventions are mixed: verb_noun (discover_tools, ask_library, find_precedent, check_tool_fit), noun_verb (datasets_list, datasets_upload, reports_list, reports_view), bare nouns (about, schedules, warehouse, my_objects) and a path_* namespace prefix for the routing tools. Singular/plural is also inconsistent (report_cards vs reports_*, dataset vs datasets_*). Readable but not predictable.
At 27 tools this exceeds the comfortable range for a single server, and the excess comes largely from the overlapping path_* router family and the duplicated status/listing tools rather than from distinct capabilities. The domain is genuinely broad (datasets, reports, builds, schedules, warehouse), but several tools could be merged into multi-action endpoints like schedules already does.
Coverage across the lifecycle is strong: ingest (datasets_upload), discovery (discover_tools, my_objects), estimation/ordering (estimate, bespoke, tool_run, rerun, reuse), delivery reads (package_status, report_cards, reports_view) and standing schedules. Gaps are modest but real: no delete/rename for datasets or reports, no build cancellation, and no way to modify an already-saved analysis other than rerunning it.
Available Tools
27 toolsaboutCRead-onlyIdempotentInspect
Platform documentation and info: how it works (Answer, Analytics, Custom Analytics), usage.
Inputs: topic (required).
account_linkARead-onlyIdempotentInspect
Direct 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.
Inputs: section.
adjust_estimateAInspect
Apply the user's layout wishes to the estimate's page through the layout agent; a new named arrangement, nothing overwritten, no number changes.
Inputs: estimate_id (required), instructions (required).
agent_advisorBRead-onlyIdempotentInspect
AI help desk: which analysis fits your question, interpreting results, fixing errors. Multi-turn.
Inputs: question (required).
ask_libraryARead-onlyIdempotentInspect
Ask a question across all your delivered analyses: a synthesized answer with citations back to specific reports.
Inputs: question (required).
build_statusARead-onlyIdempotentInspect
Check 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.
Inputs: pipeline_id, track_token.
check_tool_fitBRead-onlyIdempotentInspect
Before 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.
Inputs: tool_name (required), dataset_ref (required), objective.
datasets_listARead-onlyIdempotentInspect
List and search your uploaded datasets, with fuzzy matching on name, description, and tags. Returns each dataset's uuid:// reference (the usage field) for use as dataset_ref in path_resolver and path_tool_run. The id alone ('uuid://dsv2_...') also works for your own datasets and the platform sample; dataset_key may be null for the sample, which is normal.
Inputs: limit, search.
datasets_uploadAInspect
Get 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.
Inputs: data, expires_in, replace_ref.
discover_toolsARead-onlyIdempotentInspect
Browse 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.
Inputs: query.
find_precedentBRead-onlyIdempotentInspect
Before 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.
Inputs: objective (required), k, dataset_ref.
my_objectsBRead-onlyIdempotentInspect
List and search the objects you own across every question: the curated charts, tables and figures of each delivered package, grouped by objective.
Inputs: limit, query, include_dropped.
package_statusARead-onlyIdempotentInspect
Read an analytics package back: status, every run under it, the report link once delivered.
Inputs: package_id (required).
path_answerARead-onlyIdempotentInspect
A 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.
No key yet? Call it with objective and data (a small table, up to 200 rows): a read of that table comes back now, nothing stored. Sign-in is needed to save, re-run, or ask for more than a read.
Inputs: objective (required), data, dataset_ref, resolution_id.
path_bespokeAInspect
Order 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.
Inputs: estimate_id (required), idempotency_key (required), tool_names, resolution_id, +1 more.
path_estimateCInspect
A 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.
Inputs: objective (required), dataset_ref (required), tool_names, completeness, +2 more.
path_rerunBInspect
Run a delivered analysis again, on its own dataset or a new one: the same tools and mappings, no rebuild. package_id may also be the person's own report link (a /rpt/ link or its rpt_ token) or estimate id (est_); it reruns their newest delivered package for it. Time: as path_resolver quotes.
Inputs: package_id (required), dataset_ref, resolution_id, idempotency_key.
path_resolverARead-onlyIdempotentInspect
Which 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.
Inputs: objective (required), door, meta, dataset_ref.
path_reuseBRead-onlyIdempotentInspect
Hand back the report already delivered for this question on this data. Time: as path_resolver quotes.
Inputs: objective (required), dataset_ref (required), resolution_id.
path_tool_runBInspect
Run one or more tested library tools on this dataset, with charts and a written report. No custom build. Time: as path_resolver quotes.
Inputs: objective (required), tool_names (required), dataset_ref (required), estimate_id, +4 more.
report_cardsBRead-onlyIdempotentInspect
Browse a delivered report's individual cards (charts, tables, insights) inline in chat.
Inputs: processing_id (required).
reports_listARead-onlyIdempotentInspect
Your report library: every analysis delivered, with status and links. Pass semantic_query to search report content in plain language. A delivered package is read with package_status and my_objects.
Inputs: limit, semantic_query.
reports_viewARead-onlyIdempotentInspect
Get a shareable browser link for a report, viewable without authentication.
Inputs: processing_id (required).
review_estimateCRead-onlyIdempotentInspect
The 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.
Inputs: estimate_id (required).
schedulesADestructiveInspect
Standing 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'.
Inputs: action (required), cadence, tool_name, dataset_ref, +2 more.
tools_schemaARead-onlyIdempotentInspect
Get an analysis's parameter schema. ALWAYS call before path_tool_run.
Inputs: tool_name (required).
warehouseBRead-onlyIdempotentInspect
Query 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).
Inputs: action (required), query, params, question.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
AI data analyst: ask about your Excel, CSV, GA4 or database data and get charts and dashboards back
Valid and reliable data engineering and statistical analysis without hallucinations.
Connect your ads, shop, analytics, social, CRM and finance platforms once, then let Claude, ChatGPT, Cursor or any MCP client read, join and explain your numbers. Public statistics from the World Bank, IMF, Eurostat, OECD, WHO and SEC filings come as context, searchable and chartable from the same tools. Read-only by design, every number carries its source.
Clean messy tabular data and render publication-ready PNG charts from your AI assistant.
Related MCP Servers
- AlicenseAqualityBmaintenanceEnables AI assistants to run verified statistical and analytics computations—including hypothesis tests, A/B testing, descriptive summaries, and sample-size planning—directly on local CSV, TSV, Excel, and Parquet files of any size. Results include effect sizes, confidence intervals, plain-English interpretations, and assumption warnings, with optional independent checks.2372 npmMIT
- AlicenseNot gradedqualityBmaintenanceEnables natural-language-driven analytics over CSV/Parquet or built-in data by decomposing questions into analytical tasks, running them via deterministic DuckDB and SciPy tools, and publishing only claims verified against the underlying rows.MIT
- AlicenseNot gradedqualityDmaintenanceProvides a virtual statistician for AI agents, offering real statistical methods such as design of experiments, hypothesis testing, regression, and process control. It includes an advisor tool to recommend appropriate analyses and generates plain-language interpretations of results.MIT
- AlicenseAqualityCmaintenanceEnables AI agents to perform reproducible, verifiable statistical analysis through 25 deterministic tools for descriptive statistics, hypothesis testing, regression, clustering, time-series forecasting, and Chinese-labeled plotting.301MIT
Glama MCP Gateway
Add one secure layer between your agents and this server.