Skip to main content
Glama
inite-ai

inite-diagnostic

Official
by inite-ai
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Hybrid

INITE Diagnostic — a process audit your agent can run

Point an assistant at a business process and get back what it costs today, where it breaks first, and what to automate next.

> Our WhatsApp enquiries take until morning to answer. Is that worth fixing?

  start_audit(language: "en")        → audit_token: 9f2c…, first question
  answer_audit(field: "channels", value: "whatsapp, instagram")
  answer_audit(field: "dailyInquiries", value: "50-100")
  …
  answer_audit(finish: true)         → findings

It is the same audit that runs at inite.solutions/en/audit.

Two depths

Free — eight questions about one process. Pick the thing your people still do by hand. The interview maps it and says what it costs now and what changes if it runs itself. No account needed in the browser; from an agent, the interview and the arithmetic need none either — see Works before you sign in — and the reading itself needs one.

Premium — forty-three slots across the whole business, grouped into strategy, marketing, operations, finance and technology. The interview has a budget of thirty-five questions against those forty-three slots, so it must leave some unasked, and choosing which is the part worth having a model for. It routes by the share of each area still open, not by the count, so one expert cannot conduct two thirds of the conversation.

The first eight slots of a premium run are the free eight, unchanged. An audit that upgrades mid-way is not asked them twice.

Related MCP server: compliance-shield-mcp

Works before you sign in

Two of the tools run entirely on your machine. No account, no allowance, no call home.

diagnostic_questions hands over the interview itself — the eight things a diagnostic has to establish, in the words they are asked in — and your assistant conducts it, in the person's own language, with options that look like their industry. read_answers then does the arithmetic on what came back.

> Eighty enquiries a day between the two of us, mostly WhatsApp, kept in a spreadsheet.

  read_answers(answers: {...})

  From what you have been told:
    80 enquiries a day across 2 people — 40 each.
    12 of them become leads — 15% of what arrives.
    3 channels enquiries arrive on. The record of them: a spreadsheet.

  That is the arithmetic. What it cannot do is say what to automate first.

The split falls where the competences do. A model conducts an interview far better than it divides eighty by two and remembers what the range said, so the caller asks and this counts — and every assumption it had to make is printed beside the result ("read 50-100 as 75").

Signing in adds the audit itself: the next question chosen from everything already said, the findings written against them, a run saved under your account that you can come back to, and the forty-three question depth.

Install

Claude Desktop, Cursor, or any client that launches a stdio server:

{
  "mcpServers": {
    "inite-diagnostic": {
      "command": "npx",
      "args": ["-y", "@inite/diagnostic"]
    }
  }
}

Then, when you want the audit rather than the arithmetic:

npx @inite/diagnostic login

That opens a browser, you approve, and the token is stored at ~/.config/inite/mcp-diagnostic.json with owner-only permissions. Authorization code with PKCE over a loopback redirect, the flow RFC 8252 prescribes for a native app. Nothing is written to the repository and no secret ships in the package.

Its own file, not the one @inite/visibility writes. Both tokens are issued by the same authorization server and belong to the same person, and neither works in the other's place: RFC 8707 binds each one to the resource it was asked for. Sharing a file would mean the second login silently replaced the first one's token with something that 401s. For the same reason this package reads INITE_DIAGNOSTIC_TOKEN before INITE_TOKEN.

Tools

tool

what it does

account

diagnostic_questions

The eight fields, in the words they are asked in, for you to interview from

no

read_answers

The arithmetic on what you collected, with every assumption stated

no

start_audit

Begins the interview, returns the first question and an audit_token

yes

answer_audit

Records one answer against the field the question named, returns the next question — or the findings when the interview is over

yes

get_audit

Depth, what was answered, what was declined, what is still open, and the findings if they exist

yes

upgrade_audit

Spends a paid run if the account has one; otherwise returns a checkout link

yes

upgrade_audit deliberately stops short of buying. With nothing paid for on the account it hands back a URL for a person to open. An agent is not given a way to spend somebody's money unattended.

Answers the model does not have

"__skip__" is a valid answer and a better one than a guess. A guessed answer produces a confident wrong finding, which is worse than a gap the audit can name — and the findings say what they could not tell rather than inventing it.

Fields are a closed list

Every question names the field it fills, and that name comes from a fixed list. The model chooses which slot to raise next, how to word it and what to offer as answers; it does not choose what the answers are called. This is enforced by the schema rather than checked afterwards — the field is an enum built per call from what is still missing, so a question about anything else cannot be expressed.

That constraint exists because the version without it failed in a specific way: the panel stayed empty while the visitor answered, and the lead reached the CRM as a wall of JSON under "Industry: N/A".

The full list, generated from the server's own definitions, is in SLOTS.md.

Connect without the package

A client that speaks the MCP authorization flow can talk to the remote server directly. There are no local tools that way — the two above live in the package — and every call needs a token.

{
  "mcpServers": {
    "inite-diagnostic": {
      "type": "http",
      "url": "https://inite.solutions/api/mcp"
    }
  }
}

Authentication

Every call to the remote server needs a bearer token, and the only thing available without one is how to get a token. The two local tools need nothing.

An unauthenticated request returns 401 with a WWW-Authenticate header pointing at /.well-known/oauth-protected-resource, which names auth.inite.ai as the authorization server. A client that speaks the MCP authorization flow walks that chain on its own: it registers, a human approves in a browser, and every run after that belongs to somebody.

An agent is the same person arriving through a different door, so the quota, the entitlement and the audit rows are the account's own — not a second class of user with a separate allowance.

Registry

Published as solutions.inite/inite-diagnostic. The namespace is proved by an ed25519 key served at /.well-known/mcp-registry-auth.

The manifest that publishes it lives beside the server itself rather than here, so there is one copy of it and no way for the two to disagree. This repository is the readable half: what the server is, what it asks, and what it will not do.

The rest of the family

server

what it is for

ai.inite/inite-visibility

Whether the answer engines can see a website

club.inite/inite-club

Membership, events, the shared workspace

studio.inite/ideaudit-tools

The scoring behind an audit allowed to say no

io.github.inite-ai/inite-brain-service

Bitemporal memory for agents

License

MIT. See LICENSE.

Available Tools

2 tools
diagnostic_questionsAInspect

The eight things a process diagnostic has to establish, in the order they are usually asked. Use them to interview the person yourself — one question at a time, in their language, with options that look like their industry rather than a generic list. Then pass what you collected to read_answers. Runs locally, no account needed.

ParametersJSON Schema
NameRequiredDescriptionDefault

No parameters

TDQS

A3.8/5.0
Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description must carry behavioral disclosure. It states the tool runs locally and needs no account, which is useful. However, it does not fully clarify what the literal output of invoking the tool is, such as whether it returns a list of questions or a scripted interview guide.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is compact and each sentence earns its place: it defines the content, gives practical interviewing guidance, names the next tool, and notes the local execution. It could be slightly tighter, but there is no waste.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool has no required inputs, no annotations, and no output schema, the description covers the essential workflow: invoke it to get diagnostic questions, conduct the interview, and feed results to read_answers. The only small gap is the absence of explicit detail about the returned format or that the tool itself performs no analysis.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The tool has zero parameters, so Parameter Semantics are not a burden on the description. The schema already confirms there are no inputs, and the description appropriately focuses on how to use the tool's output rather than on parameters.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly identifies the tool as providing the eight things a process diagnostic must establish, in a defined order. It distinguishes itself from read_answers by stating that this tool is for collecting interview answers while read_answers handles what was collected.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description gives concrete usage guidance: interview the person yourself, ask one question at a time, adapt the language and options to their industry, then pass the collected answers to read_answers. It does not explicitly state when not to use the tool, but the workflow is clear.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

read_answersAInspect

Do the arithmetic on a set of collected answers: enquiries per person, the share that become leads, how many channels arrive without one record, and which of the eight are still blank. Every assumption it had to make is printed beside the result. It stops short of saying what to automate — that is the audit, and it needs an account. Runs locally, no account needed.

ParametersJSON Schema
NameRequiredDescriptionDefault
answersYesWhat you have collected, keyed by field: {"industry": "…", "dailyInquiries": "50-100", …}. Use "__skip__" for a question that was declined — it is a better answer than a guess.

TDQS

A4.2/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full behavioral burden. It discloses that assumptions are printed beside results and that the tool runs locally with no account needed, which signals a safe, non-remote, low-privilege operation. It does not detail failure behavior or exact output shape, but the described behavior is unusually transparent for a tool without annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Three focused sentences: the first names the operation and outputs, the second clarifies output transparency, and the third bounds scope and access requirements. Every sentence contributes distinct useful information with no repetition.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a single-parameter local computation tool, the description covers what it does, what it returns conceptually, its assumptions behavior, and its access requirements. Without an output schema, more detail on exact result formatting might help, but the listed computed metrics are sufficient for an agent to judge fit.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema already documents the 'answers' parameter fully, including the '__skip__' convention, so schema coverage is 100%. The description adds context about what arithmetic will be performed but does not materially enrich parameter semantics beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

Description names a specific operation ('Do the arithmetic on a set of collected answers') and lists concrete outputs: enquiries per person, lead share, channels without a record, and blank fields. It also distinguishes itself from the audit, making its scope clear.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The intended context is clear: use this after collecting answers, locally and without an account. It also states an exclusion ('stops short of saying what to automate — that is the audit'), which helps an agent avoid reaching for this tool when automation recommendations are needed, though it does not explicitly name the sibling tool as an alternative.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

  1. 2 tool updatesv1.1.0
    • First observeddiagnostic_questions
    • First observedread_answers
Deploy Server
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

TDQS

A3.9/5.0

Scored across 2 tools

Disambiguation5/5

diagnostic_questions is the interview/collection step, while read_answers is the analysis step that consumes the collected data. Their roles are complementary and clearly distinct, with an explicit handoff. No meaningful overlap exists.

Naming Consistency4/5

Both names are readable snake_case, but read_answers follows a verb_noun pattern while diagnostic_questions is a noun phrase. The inconsistency is minor and does not create confusion.

Tool Count3/5

Two tools is thin for a general-purpose server, but it fits the narrow diagnostic workflow. Each tool has a clear purpose, yet the set feels minimal and borderline rather than fully scoped.

Completeness3/5

The server covers gathering diagnostic questions and reading the answers, but it explicitly stops before the audit/recommendation step, which is a notable gap for a diagnostic workflow. The handoff is clear, but the missing automation recommendation leaves the process feeling incomplete.

Maintenance

ActivityMaintained
ResponsivenessNo issues

Resources

Related MCP Connectors

Related MCP Servers

  • ai-visibility-mcp

    rccola990-cloud
    A
    license
    Not graded
    quality
    B
    maintenance
    Enables AI agents to check whether AI assistants recommend a brand and audit a site's AI-agent readiness, providing visibility scores and specific gaps.
    MIT

  • SoftAuto

    guangfubill-crypto
    A
    license
    Not graded
    quality
    A
    maintenance
    Enables AI agents to perform deterministic Windows desktop and browser automation through MCP, using pre-validated UI Automation and DOM locators for fast, stable execution of ERP and business workflows.
    1
    MIT

  • automation-audit

    zuperRuslana
    F
    license
    B
    quality
    C
    maintenance
    Enables AI assistants to evaluate business processes for automation by collecting discovery answers, calculating labor costs, scoring automation potential, and saving completed audits to a local SQLite database.
    8
    -