Which integrations are available for this server?

Allows generating branded talent documents directly within Perplexity by connecting to the Formatix MCP server.

How do I use Formatix AI MCP Server?

1. Click on "Install Server". 2. Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state. 3. In the chat, type @ followed by the MCP server name and your instructions, e.g., "@Formatix AI MCP Server Generate a branded candidate profile from this LinkedIn text." That's it! The server will respond to your query, and you can continue using it as needed. Here is a step-by-step guide with screenshots.

Formatix AI MCP Server

Official

by FormatixAI

Overview Schema Related Servers Score Discussions

JavaScript

Hybrid

Formatix AI — MCP Server

The only AI that automates and personalizes any branded talent document — not just CVs.

Turn a CV, a LinkedIn profile, or structured data into assessment reports (Hogan, psychometric, CEO & leadership), progression reports, executive profiles, candidate shortlists, client submittals, proposals and RPO reports — exported as DOCX, PPTX, PDF or Excel, perfectly on-brand.

Connect Formatix to Claude, ChatGPT, Perplexity, Cursor, Claude Code — or any MCP-compatible AI agent — and let the AI generate the finished, client-ready document for you.

npm License: MIT Trustpilot GitHub

Website: https://formatix.ai · Reviews: Trustpilot

Why Formatix is different

Every other "CV formatter" stops at one CV → one Word document. Formatix is the only platform that templatizes and automates the documents nobody else does, across every format and use case:

Document type	Examples	Formats
Assessment reports	Hogan reports, psychometric reports, CEO assessment, leadership assessment	DOCX · PPTX · PDF
Progression reports	Succession & talent-review packs, 9-box, promotion cases	DOCX · PPTX · XLSX
Executive profiles	One-page bios, branded candidate profiles, blind/anonymized CVs	DOCX · PPTX · PDF
Shortlists & decks	Multi-candidate shortlist decks, longlists, slate presentations	PPTX
Client deliverables	Client submittals, proposals, RPO reports, market & comp intelligence	DOCX · PPTX · PDF · XLSX

Every document is generated from your own branded template — fonts, colours, logos and layout preserved exactly.

Related MCP server: KnowledgeBaseMCP

Who uses it

Executive search firms — client-branded profiles, shortlist decks and proposals in minutes.
In-house exec & leadership recruiting (TA) — board-ready candidate slates and assessment summaries.
Talent mapping / RPO teams — market maps, comp benchmarking, RPO reporting.
HR / People teams — succession planning, talent reviews and promotion packs.

Three ways to use Formatix

Remote MCP — point ChatGPT, Claude or Perplexity at the hosted Formatix MCP endpoint.
npx (this package) — run locally inside Claude Desktop, Cursor or Claude Code.
Chrome extension — capture any LinkedIn profile and turn it into a polished resume in one click. → https://formatix.ai

Quick start

Get a free API key (company email)

Free access requires a company email — personal inboxes (gmail, outlook, yahoo, proton…) are not eligible.

In any connected AI client, just ask it to "claim free Formatix access with my email you@yourcompany.com" — the claim_access tool issues a key instantly, or
Sign up at https://formatix.ai and create a key in Settings → API keys.

Set the key as FORMATIX_API_KEY in the configs below.

Claude Desktop / Claude Code

claude_desktop_config.json (or .mcp.json for Claude Code):

{
  "mcpServers": {
    "formatix": {
      "command": "npx",
      "args": ["-y", "@formatix-ai/mcp"],
      "env": {
        "FORMATIX_API_KEY": "fxi_your_key_here"
      }
    }
  }
}

Cursor

~/.cursor/mcp.json:

{
  "mcpServers": {
    "formatix": {
      "command": "npx",
      "args": ["-y", "@formatix-ai/mcp"],
      "env": { "FORMATIX_API_KEY": "fxi_your_key_here" }
    }
  }
}

ChatGPT / Perplexity (remote connector)

Add a custom connector / MCP server pointing at the hosted endpoint:

https://platform.formatix.ai/mcp

Authenticate with your Formatix account (OAuth) or paste your fxi_ API key when prompted.

Tools

Tool	What it does
`list_document_types`	List every document Formatix can generate (assessment reports, profiles, shortlists, proposals…) with available formats. Call this first.
`generate_document`	The hero. Any source text → any branded document in DOCX/PPTX/PDF/XLSX. Returns a `record_id`.
`format_from_linkedin`	LinkedIn profile text → polished resume / candidate profile.
`check_status`	Poll a `record_id`; returns the download link when the document is ready.
`claim_access`	Get a free API key with your company email.

Typical agent flow

list_document_types()                         → choose a template_id + template_type
generate_document(source_text, template_id,   → returns record_id
                  template_type, output_format)
check_status(record_id)                        → "Formatted" + download_url
→ hand the download_url back to the client

Configuration

Env var	Default	Purpose
`FORMATIX_API_KEY`	(none)	Your `fxi_` key. Without it, only `claim_access` works.
`FORMATIX_API_BASE`	`https://platform.formatix.ai`	Override for testing against another environment.

How it works

This package is a thin client. All formatting, AI extraction and rendering run on the Formatix platform; this server simply exposes a small, agent-friendly set of tools over the Model Context Protocol. No credentials are stored in this repo — you supply your own key.

License

MIT © Formatix AI Ltd

Available Tools

5 tools

check_statusA

Check whether a generated document is ready and get its download link. Status is 'Processing' (keep polling), 'Formatted' (ready — share the download_url with the client), or 'Failed - '.

ParametersJSON Schema

Name	Required	Description	Default
`record_id`	Yes	The record_id returned by `generate_document` or `format_from_linkedin`.

TDQS

A4.3/5.0

Behavior4/5

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

With no annotations, the description fully discloses the polling behavior, status interpretations, and that it returns a download link. It does not mention rate limits or resource consumption, but for a read-only polling tool this is sufficient.

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?

Two sentences: first states purpose, second explains status values and actions. No redundancy, every word contributes.

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

Completeness5/5

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

Given the simple single-parameter tool with no output schema, the description completely covers polling behavior, status values, and appropriate follow-up actions, making it fully self-contained.

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?

Schema coverage is 100% and the schema description for record_id already specifies it comes from generate_document or format_from_linkedin. The tool description adds no extra parameter info, so baseline 3 is appropriate.

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?

The description clearly states the verb 'check' and the resource 'generated document', and distinguishes itself from sibling tools like generate_document and format_from_linkedin which are for generation, not status polling.

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 explains the three possible statuses and how to react: poll for 'Processing', share URL for 'Formatted', and treat 'Failed' accordingly. It implies usage after generation tools via the parameter description, but doesn't explicitly state when to call or list alternatives.

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

claim_accessA

Get FREE Formatix access using your COMPANY email. Personal inboxes (gmail, outlook, yahoo, proton, etc.) are not eligible. Returns a free API key — treat it as a secret: store it as FORMATIX_API_KEY in your MCP config rather than leaving it in chat history.

ParametersJSON Schema

Name	Required	Description	Default
`company_email`	Yes	Your work/company email address. Personal inboxes are rejected.

TDQS

A4.2/5.0

Behavior4/5

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

No annotations, but description discloses that the tool returns an API key, its sensitivity, and storage recommendation. Adequate for a free access claim tool.

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?

Two sentences with no wasted words. Front-loads purpose and includes actionable guidance. Excellent conciseness.

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?

Covers purpose, eligibility, and output handling. With simple input and no output schema, it is sufficient. Could mention one-time use, but not critical.

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?

Schema coverage is 100% with clear property description. Description adds context about eligibility but doesn't enhance parameter understanding beyond schema. Baseline 3 is appropriate.

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?

Clearly states the action 'Get FREE Formatix access' and the resource, distinguishing it from sibling tools like generate_document or check_status.

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?

Explicitly specifies eligibility (company email only) and implicitly provides context for when to use. Could mention alternatives if already have access, but still strong.

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

format_from_linkedinA

Turn a LinkedIn profile into a polished, branded resume or candidate profile. Paste the visible profile text as profile_text. (To capture LinkedIn profiles automatically inside the browser, install the Formatix Chrome extension.) Returns a record_id; poll check_status.

ParametersJSON Schema

Name	Required	Description	Default
`template_id`	No	Optional template id from `list_document_types`. If omitted, call `list_document_types` first to choose a profile/resume template.
`profile_text`	Yes	The text content of the LinkedIn profile (paste what is visible on the page).
`output_format`	No	Output file format. Default docx.	docx
`template_type`	No	The template's type. Required if template_id is supplied.
`candidate_name`	No	Candidate display name. Optional.

TDQS

A3.5/5.0

Behavior2/5

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

With no annotations, the description carries the full burden. It discloses async behavior ('Returns a record_id; poll check_status') and indicates that input must be pasted text rather than auto-scraped. However, it omits critical details such as whether the tool mutates data, authentication requirements, rate limits, or error handling. The description does not contradict any annotations (none provided).

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?

The description is extremely concise: two sentences and a parenthetical. It front-loads the core purpose and async workflow. Every sentence adds necessary information with no redundancy.

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

Completeness3/5

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

Given the tool has 5 parameters, no output schema, and involves async polling, the description provides a coherent high-level workflow (paste text → record_id → poll). However, it lacks specifics about the output types (docx/pptx/xlsx), the role of template_type, and what constitutes valid input. Error conditions and the overall user context are not addressed.

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?

Schema coverage is 100%, so baseline is 3. The description complements the schema by explaining the main parameter (profile_text) and providing guidance on template_id ('call list_document_types first'). Other parameters (candidate_name, output_format, template_type) are not elaborated beyond the schema. Overall, the description adds marginal value.

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?

The description uses a specific verb ('Turn') and clearly identifies the resource ('LinkedIn profile') and the output ('polished, branded resume or candidate profile'). It also references the polling workflow via a sibling tool, which helps distinguish it from other tools.

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

Usage Guidelines3/5

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

The description implies usage for LinkedIn profiles and suggests installing a Chrome extension for automated capture, but it does not explicitly state when to use this tool versus alternatives like generate_document or what scenarios to avoid. No exclusions or comparisons to siblings are provided.

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

generate_documentA

Generate a branded, personalized talent document from candidate text. Works for any document type returned by list_document_types — assessment reports, executive profiles, shortlists, proposals, etc. Returns a record_id; poll check_status until the document is ready to download.

ParametersJSON Schema

Name	Required	Description	Default
`source_text`	Yes	The candidate's CV text, profile, or source content to format. Plain text.
`template_id`	Yes	Template id from `list_document_types`.
`output_format`	No	Output file format. Default docx.	docx
`template_type`	Yes	The template's type, as shown by `list_document_types`.
`candidate_name`	No	Candidate display name used in the file/output. Optional.

TDQS

A4/5.0

Behavior3/5

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

With no annotations, the description carries the full burden. It discloses that the tool is asynchronous (returns a record_id, requires polling check_status). It does not mention authentication, error handling, or side effects, but for a generation tool the async behavior is the key trait.

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?

Two sentences with no wasted words. The first sentence states the primary action, the second adds scope, workflow, and sibling reference. Information is front-loaded.

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 5 parameters, no output schema, and absent annotations, the description adequately covers the tool's purpose, usage flow, and key parameters. It mentions the async polling pattern and references sibling tools, though it could briefly note error scenarios or limits.

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?

All 5 parameters are described in the schema (100% coverage), so baseline is 3. The description adds value by referencing list_document_types for template_id and template_type, and noting default output_format, but largely mirrors schema descriptions.

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?

The description clearly states the tool generates a branded, personalized talent document from candidate text, and specifies it works for any document type from list_document_types. It distinguishes itself from siblings like format_from_linkedin and check_status by naming the specific resource and output.

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 explains when to use this tool: after selecting a document type via list_document_types, and then polling check_status for the result. While it doesn't explicitly state when not to use it, the context is clear and the workflow is outlined.

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

list_document_typesA

List the branded talent documents Formatix can generate — assessment reports (Hogan, psychometric, CEO & leadership), progression reports, candidate profiles, shortlists, client submittals, proposals and RPO reports — each with its available output formats (DOCX, PPTX, PDF, XLSX). Call this first to choose a template_id for generate_document.

ParametersJSON Schema

Name	Required	Description	Default
No parameters

TDQS

A4.6/5.0

Behavior4/5

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

No annotations are provided, so the description carries the full burden. It discloses the tool lists documents with formats, which is a read-only operation. While it doesn't explicitly state it is non-destructive or idempotent, the nature of listing is inferred. A score of 4 is appropriate as it is clear enough for a simple list tool.

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 a single sentence that efficiently conveys purpose and usage. It lists examples and gives guidance without unnecessary words. Slightly more structure (e.g., splitting into purpose and usage) could improve readability, but it is already concise.

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

Completeness5/5

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

With no output schema, the description adequately explains what the response contains (document list with output formats) and why to call it. It covers the essential information for an agent to use the tool correctly in the workflow.

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 input schema has zero parameters, so schema coverage is 100%. The description does not need to add parameter info, hence baseline 4 applies.

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?

The description clearly states the tool lists branded talent documents with output formats, using specific examples. It distinguishes from siblings by directly mentioning its role in selecting a template_id for generate_document.

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

Usage Guidelines5/5

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

The description explicitly says 'Call this first to choose a template_id for generate_document', providing clear when-to-use and a link to a sibling tool, making usage unambiguous.

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. Dates show when Glama detected each change.

5 tool updatesv0.1.1Jul 30, 2026
- First observedcheck_status
- First observedclaim_access
- First observedformat_from_linkedin
- First observedgenerate_document
- First observedlist_document_types

Install Server

RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

TDQS

A4.2/5.0

Disambiguation5/5

Each of the five tools has a clearly distinct purpose: claiming access, listing document types, generating documents from text, formatting from LinkedIn, and checking status. No two tools overlap in functionality.

Naming Consistency5/5

All tool names follow a consistent snake_case verb_noun pattern (e.g., claim_access, list_document_types, generate_document). The naming is uniform and predictable.

Tool Count5/5

With only five tools, the server is well-scoped for a focused document generation service. Each tool serves an essential step in the workflow without extraneous or missing functions.

Completeness5/5

The tool surface covers the entire flow: access, template selection, document generation from two sources, and status polling. No obvious gaps for the stated purpose.

Maintenance

ActivityStale

ResponsivenessSyncing

Resources

Need Help?

Related Servers

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Connectors

DocRocketOAuth
io.github.Crash-ept
Generate on-brand proposals, reports, and contracts instantly. Auto-extracts brand from any URL.
Workplace & Productivity Content Management Systems
2
docx-document-generator-proposal-contract-markdown
io.github.theluckystrike
Create real Word .docx files from your AI chat: proposals, quotes, contracts, statements of work.
Workplace & Productivity App Automation
1
emplusx
com.emplusx
Finished, on-brand .pptx and .docx from a brief - quality-gated by an agentic consulting team.
Workplace & Productivity Marketing Autonomous Agents
1
Clueso A
io.clueso
Make videos and docs with your AI agent — describe what you need, every output stays editable.
Multimedia Processing Content Management Systems AI & Machine Learning
4025

Related MCP Servers

Report Builder MCP Server
Workplace & Productivity Developer Tools
nathanwolfe2208
F
license
A
quality
D
maintenance
Formats AI agent outputs into professional reports, emails, and documents with branding, quality validation, and executive summaries for enterprise AI operations.
Updated 10 months ago (2025-11-06 00:22 UTC)
5
-
KnowledgeBaseMCP
File Systems Developer Tools Documentation Access
mehmetozcan-zz
A
license
Not graded
quality
D
maintenance
Enables AI assistants to extract and analyze text content from various document formats (PDF, DOCX, PPTX, XLSX) in local knowledge bases, and create new formatted Word and Excel documents with structured data and reports.
Updated a year ago (2025-07-02 09:34 UTC)
5
MIT
Document Generator MCP
Developer Tools Workplace & Productivity Content Management Systems
thiagotw10
A
license
B
quality
D
maintenance
Enables AI agents to generate professional Word and PDF documents with support for Markdown, syntax highlighting, and smart pagination. It features automatic JSON detection and responsive A4 formatting for creating high-quality technical reports and manuals.
Updated a year ago (2025-10-09 16:34 UTC)
2
242
7
MIT
docforge-mcp
Workplace & Productivity Developer Tools
filhocf
A
license
B
quality
D
maintenance
Enables complete Office document lifecycle management for AI agents, including creation, editing, conversion, and templating of DOCX, XLSX, PPTX, PDF, and EML files.
Updated a month ago (2026-07-21 19:04 UTC)
40
MIT

Latest Blog Posts

Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)
By Om-Shree-0709 on July 25, 2026.
mcp
Agent Identity
OAuth 2.1
Your AI Chatbot Just Exposed Your CEO's Salary to an Intern
By Om-Shree-0709 on July 2, 2026.
Agent Identity
MCP Security
OAuth Delegation
Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)
By Om-Shree-0709 on June 30, 2026.
Agentic Ai
Prompt Injection
WebAssembly

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/FormatixAI/mcp-server'

If you have feedback or need assistance with the MCP directory API, please join our Discord server

Formatix AI — MCP Server

Why Formatix is different

Who uses it

Three ways to use Formatix

Quick start

Get a free API key (company email)

Claude Desktop / Claude Code

Cursor

ChatGPT / Perplexity (remote connector)

Tools

Typical agent flow

Configuration

How it works

Links

License

Available Tools

Tool Schema Changelog

Maintenance

Resources

Looking for Admin?

Related MCP Connectors

Related MCP Servers

Latest Blog Posts

MCP directory API