Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

MCP Analytics

REMOTE · API.MCPANALYTICS.AI

A statistical analyst in your AI chat: bring data and a question, get a citable, re-runnable report.

0 this week 83 Trust /100

Last scanned (14 hours ago)

Scores higher than 83% of remote servers

Reachable. Last reached 21 Nov 2026.

Category Data and Analytics

Trust breakdown (7 categories)

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. How we score → Why this is hard to score →

Endpoint Security83
Transport & Reachability100
Schema Quality & AI Usability69
  • AI-judged instruction clarity (good).Pass
  • Tool/resource definitions use about 2716 tokens (~100/item across 27 items; 27 tools + 0 resources), lean.Pass
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management98
  • Stability check failed: schema churn in the 30 days we've observed: 0 tool removals, 1 breaking changes, 0 auth/transport breaks, 0 additions. See how to fix → Fail
Tool Coverage87
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 62% of tool parameters carry a description.Partial
Tool Safety100
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • We read all 27 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
  • An AI judge read all 28 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities20
  • Spec-recency check failed: implements MCP spec 2024-11-05; the latest is 2026-07-28. See how to fix → Fail
What we tested

Checks we ran (13)

  • TLS certificate
  • Authorization
  • HTTPS
  • HSTS header
  • DNSSEC
  • Transport
  • Schema quality
  • Stability
  • Tool coverage
  • Injection markers
  • Destructive annotations
  • Judged manipulation
  • MCP protocol

Does not apply to this hosted endpoint (2)

  • Supply Chain SecurityScored on package channels only. This is a hosted endpoint, so there is nothing to install or inspect.
  • Provenance & TransparencyScored on package channels only. This is a hosted endpoint, so there is nothing to install or inspect.

The score does not measure everything. What the score does not measure →

Changelog

Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

  • 20 Nov 26 0
    • The server rewrote its instructions, which are the text every model session reads security
    • Tool “reports_list” rewrote its description, which is the text the model reads security
    • “path_rerun” added an optional parameter “idempotency_key” cosmetic
    • “build_status” reworded the description of “pipeline_id” cosmetic
    • “datasets_upload” reworded the description of “replace_ref” cosmetic
    • “datasets_upload” reworded the description of “expires_in” cosmetic
  • 13 Nov 26 +4

    No change was recorded against any check on this day. Stability & Change Management went from 69 to 94.

  • 6 Nov 26 0
    • We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
  • 2 Nov 26 0
    • Tool “path_rerun” rewrote its description, which is the text the model reads security
    • “path_rerun” reworded the description of “package_id” cosmetic
  • 1 Nov 26 0
    • The server rewrote its instructions, which are the text every model session reads security
    • Tool “path_answer” rewrote its description, which is the text the model reads security
    • “path_answer” added an optional parameter “data” cosmetic
    • “path_answer” made “dataset_ref” optional cosmetic
  • 25 Oct 26 0
    • Tool “datasets_list” rewrote its description, which is the text the model reads security
    • “path_answer” reworded the description of “dataset_ref” cosmetic
    • “path_tool_run” reworded the description of “dataset_ref” cosmetic
    • “path_reuse” reworded the description of “dataset_ref” cosmetic
    • “path_estimate” reworded the description of “dataset_ref” cosmetic
  • 15 Oct 26 0
    • Stability: unverified → fail ▼ security
    • Authorization: unverified → fail ▼ security
    • A breaking change shipped without a version bump: still 1.0.7 ▼ security
    • Tool “run_analysis” was removed ▼ security
    • Tool “answer_now” was removed ▼ security
    • Tool “create_analysis” was removed ▼ security
    • Tool “decide_path” was removed ▼ security
    • Tool “modify_analysis” was removed ▼ security
    • Tool “order_analytics_package” was removed ▼ security
    • Tool “request_estimate” was removed ▼ security
    • Tool “rerun_package” was removed ▼ security
    • Injection markers: unverified → pass ▲ security
    • Transport: fail → pass ▲ security
    • Tool “about” rewrote its description, which is the text the model reads security
    • MCP protocol: unverified → fail ▼ functional
    • Endpoint reachability: not serving MCP → reachable ▲ functional
    • Tool coverage: unverified → 100 ▲ functional
    • New tool “path_answer” functional
    • New tool “path_bespoke” functional
    • New tool “path_estimate” functional
    • New tool “path_rerun” functional
    • New tool “path_resolver” functional
    • New tool “path_reuse” functional
    • New tool “path_tool_run” functional
  • 14 Oct 26 0
    • Endpoint reachability: reachable → not serving MCP ▼ security
    • Stability: pass → unverified ▼ security
    • Authorization: fail → unverified ▼ security
    • Tool safety: pass → unverified ▼ security
    • Transport: pass → fail ▼ security
    • Capabilities: fail → unverified ▼ functional
    • Tool coverage: 100 → unverified ▼ functional
    • First check of Schema quality: unverified functional
Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 21 Nov 2026 · Probed https://api.mcpanalytics.ai/mcp/api-key

TLS valid

Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .

Subject Issuer Valid from Valid until Key Signature Serial
CN=mcpanalytics.ai CN=WE1,O=Google Trust Services,C=US 9 Oct 2026 7 Jan 2027 ECDSA 256 ECDSA-SHA256 198214f909052acc0ed7ce9c43173083
SANs: mcpanalytics.ai, *.mcpanalytics.ai
CN=WE1,O=Google Trust Services,C=US (CA) CN=GTS Root R4,O=Google Trust Services LLC,C=US 13 Dec 2023 20 Feb 2029 ECDSA 256 ECDSA-SHA384 7ff31977972c224a76155d13b6d685e3
CN=GTS Root R4,O=Google Trust Services LLC,C=US (CA) CN=GlobalSign Root CA,OU=Root CA,O=GlobalSign nv-sa,C=BE 15 Nov 2023 28 Jan 2028 ECDSA 384 SHA256-RSA 7fe530bf331343bedd821610493d8a1b

Background: What to check on a remote MCP endpoint →

DNSSEC insecure

Validation of api.mcpanalytics.ai. — Not signed

Zone DS Keys Algorithms Outcome
. Trust anchor 20326, 38696 8, 8 Verified
ai. DS published 1814 8 Verified
mcpanalytics.ai. No DS Unsigned (proven) parent-signed NSEC/NSEC3 proves an unsigned delegation
Authentication Challenged, unverified

The endpoint asked for a token, but we could not retrieve and validate the RFC 9728 metadata that tells a client how to obtain one.

Result Challenged, unverified
Enforced On tool calls
HTTP status 200

WWW-Authenticate challenge API-Key realm="https://api.mcpanalytics.ai"

API-Key realm="https://api.mcpanalytics.ai"
Header Value
x-content-type-options nosniff
x-frame-options SAMEORIGIN
referrer-policy strict-origin-when-cross-origin

Protected resource metadata

Retrieved No
Problem No resource metadata

Background: How OAuth 2.1 works in the 2026 MCP spec →

Transports 2 probes
Transport URL Outcome Status Location
streamable-http https://api.mcpanalytics.ai/mcp/api-key Verified 200
http (plaintext) http://api.mcpanalytics.ai/mcp/api-key HTTPS enforced 301 https://api.mcpanalytics.ai/mcp/api-key
MCP tools · 27 exposed · ~2,481 tokens

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →

Tool Tokens
about ~44

Platform documentation and info: how it works (Answer, Analytics, Custom Analytics), usage.

NameTypeReqDescription
topicstringyesTopic: platform, manual, connectors, or a docs section

No output schema declared.

No examples provided.

account_link ~51

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.

NameTypeReqDescription
sectionstring–Where to send the user

No output schema declared.

No examples provided.

adjust_estimate ~59

Apply the user's layout wishes to the estimate's page through the layout agent; a new named arrangement, nothing overwritten, no number changes.

NameTypeReqDescription
estimate_idstringyes–
instructionsstringyesWhat to change, in the user's words

No output schema declared.

No examples provided.

agent_advisor ~39

AI help desk: which analysis fits your question, interpreting results, fixing errors. Multi-turn.

NameTypeReqDescription
questionstringyesYour question or request

No output schema declared.

No examples provided.

ask_library ~43

Ask a question across all your delivered analyses: a synthesized answer with citations back to specific reports.

NameTypeReqDescription
questionstringyesPlain-language question to answer from your report library

No output schema declared.

No examples provided.

build_status ~65

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.

NameTypeReqDescription
pipeline_idinteger–pipeline_id from a build
track_tokenstring–Token from the tracking URL

No output schema declared.

No examples provided.

check_tool_fit ~66

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.

NameTypeReqDescription
dataset_refstringyes–
objectivestring––
tool_namestringyes–

No output schema declared.

No examples provided.

datasets_list ~116

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.

NameTypeReqDescription
limitinteger–Max results
searchstring–Search by name, description, or tags

No output schema declared.

No examples provided.

datasets_upload ~177

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.

NameTypeReqDescription
dataarray–Rows as an array of flat objects, creates the dataset in one call
expires_ininteger–Not used: an upload link always lasts 20 minutes (see expires_at)
replace_refstring–uuid://ID:KEY of an existing dataset to overwrite in place with `data` (the push/refresh mode); the previous rows are deleted, no copy is kept

No output schema declared.

No examples provided.

discover_tools ~86

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.

NameTypeReqDescription
querystring–Plain-language search over your library + the Standard Library; omit to list everything

No output schema declared.

No examples provided.

find_precedent ~76

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.

NameTypeReqDescription
dataset_refstring––
kinteger––
objectivestringyes–

No output schema declared.

No examples provided.

my_objects ~58

List and search the objects you own across every question: the curated charts, tables and figures of each delivered package, grouped by objective.

NameTypeReqDescription
include_droppedboolean––
limitinteger––
querystring––

No output schema declared.

No examples provided.

package_status ~35

Read an analytics package back: status, every run under it, the report link once delivered.

NameTypeReqDescription
package_idstringyes–

No output schema declared.

No examples provided.

path_answer ~233

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.

NameTypeReqDescription
dataarray–WITHOUT A KEY: up to 200 rows pasted inline as flat objects, e.g. [{"month":"Jan","sales":120}]. Use instead of dataset_ref.
dataset_refstring–the dataset: the `usage` value from datasets_list (uuid://ID or uuid://ID:KEY), or its id, for a dataset the caller owns or the platform sample
objectivestringyesthe question, in the person's words
resolution_idinteger–The resolution_id from path_resolver's path_input. Pass path_input as given.

No output schema declared.

No examples provided.

path_bespoke ~117

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.

NameTypeReqDescription
estimate_idstringyes–
idempotency_keystringyes–
layout_objective–––
resolution_idinteger–The resolution_id from path_resolver's path_input. Pass path_input as given.
tool_names––library tools to run alongside the build

No output schema declared.

No examples provided.

path_estimate ~141

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.

NameTypeReqDescription
completeness–––
dataset_refstringyesthe dataset: the `usage` value from datasets_list (uuid://ID or uuid://ID:KEY), or its id, for a dataset the caller owns or the platform sample
layout_objective–––
objectivestringyesthe question, in the person's words
resolution_idinteger–The resolution_id from path_resolver's path_input. Pass path_input as given.
tool_names–––

No output schema declared.

No examples provided.

path_rerun ~194

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.

NameTypeReqDescription
dataset_ref––absent = the package's own dataset
idempotency_key––send one per rerun; a retry with the same key replays the first call instead of running and charging it again
package_idstringyesA delivered package's id, or the person's own report link (/rpt/ link or rpt_ token) or estimate id (est_). Someone else's link is not found.
resolution_idinteger–The resolution_id from path_resolver's path_input. Pass path_input as given.

No output schema declared.

No examples provided.

path_resolver ~125

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.

NameTypeReqDescription
dataset_ref––absent = no data yet (the resolver asks for it)
doorstring––
metaarray–open list of {key, value}; the caller's entries are always `stated`
objectivestringyesthe question, in the person's words

No output schema declared.

No examples provided.

path_reuse ~112

Hand back the report already delivered for this question on this data. Time: as path_resolver quotes.

NameTypeReqDescription
dataset_refstringyesthe dataset: the `usage` value from datasets_list (uuid://ID or uuid://ID:KEY), or its id, for a dataset the caller owns or the platform sample
objectivestringyesthe question, in the person's words
resolution_idinteger–The resolution_id from path_resolver's path_input. Pass path_input as given.

No output schema declared.

No examples provided.

path_tool_run ~191

Run one or more tested library tools on this dataset, with charts and a written report. No custom build. Time: as path_resolver quotes.

NameTypeReqDescription
column_mapping––dataset column for each input the tool needs; absent = suggested from the data
dataset_refstringyesthe dataset: the `usage` value from datasets_list (uuid://ID or uuid://ID:KEY), or its id, for a dataset the caller owns or the platform sample
estimate_id–––
idempotency_key––send one per run; a retry with the same key replays the first call instead of running it again
module_parameters–––
objectivestringyesthe question, in the person's words
resolution_idinteger–The resolution_id from path_resolver's path_input. Pass path_input as given.
tool_namesarrayyes–

No output schema declared.

No examples provided.

report_cards ~48

Browse a delivered report's individual cards (charts, tables, insights) inline in chat.

NameTypeReqDescription
processing_idstringyesThe report's processing id, returned by path_tool_run or build_status

No output schema declared.

No examples provided.

reports_list ~69

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.

NameTypeReqDescription
limitinteger–Max results
semantic_querystring–Natural-language search over your reports' content

No output schema declared.

No examples provided.

reports_view ~40

Get a shareable browser link for a report, viewable without authentication.

NameTypeReqDescription
processing_idstringyesProcessing ID from path_tool_run / reports_list

No output schema declared.

No examples provided.

review_estimate ~60

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.

NameTypeReqDescription
estimate_idstringyes–

No output schema declared.

No examples provided.

schedules ~126

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'.

NameTypeReqDescription
actionstringyesWhat to do
cadencestring––
column_mappingobject––
dataset_refstring–create: re-runnable reference (connector:// or https://)
schedule_idinteger–cancel: from action='list'
tool_namestring–create: the analysis to schedule

No output schema declared.

No examples provided.

tools_schema ~34

Get an analysis's parameter schema. ALWAYS call before path_tool_run.

NameTypeReqDescription
tool_namestringyesName of the analysis

No output schema declared.

No examples provided.

warehouse ~76

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).

NameTypeReqDescription
actionstringyes–
paramsobject––
querystring––
questionstring––

No output schema declared.

No examples provided.

Install

How do I install the MCP Analytics server?

MCP Analytics is a hosted endpoint at https://api.mcpanalytics.ai/mcp/api-key, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

remote · api.mcpanalytics.ai

# add to Claude Code
claude mcp add --transport http ai-mcpanalytics-analytics 'https://api.mcpanalytics.ai/mcp/api-key'
Common questions

What is the MCP Analytics server?

MCP Analytics is listed in the public MCP registry as ai.mcpanalytics/analytics. A statistical analyst in your AI chat: bring data and a question, get a citable, re-runnable report. This page covers its hosted endpoint (https://api.mcpanalytics.ai/mcp/api-key).

Is the MCP Analytics server safe to use?

MCP Analytics scores 83 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

What tools does the MCP Analytics server expose?

MCP Analytics exposes 27 tools: account_link, about, agent_advisor, datasets_upload, datasets_list, and 22 more. Their descriptions and schemas cost roughly 2,481 tokens of context every time the server is loaded.

Does the MCP Analytics server require authentication?

Yes. MCP Analytics asked us for credentials when we connected, so you will need to authorise it in your MCP client before it can do anything.

Is the MCP Analytics server still maintained?

MCP Analytics is still listed as active in the MCP registry. We last reached this channel on 21 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

What did VerifyMCP test on the MCP Analytics server?

VerifyMCP ran 13 checks on MCP Analytics, covering TLS certificate, Authorization, HTTPS, HSTS header and 9 more. Supply Chain Security and Provenance & Transparency do not apply to a hosted endpoint, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.