What can you do with this server?

* search_jobs: Search for jobs using filters like title, location (city/state/country IDs or ISO codes), remote status, company, salary range, experience level, employment type, date, and more. Supports pagination. * get_job: Retrieve detailed job information, including full HTML description, by job ID. * search_companies: Find companies via fuzzy name search, website domain, or employer IDs, with optional active-status filter. * get_company: Get detailed company info and enrichment data by employer ID. * suggest_locations: Autocomplete city, state, or country names to obtain IDs for use in search_jobs geo-filters. * create_candidate_profile (prompt): Generates a structured prompt from candidate details (name, LinkedIn, website, resume) to guide job searches.

How do I use cleanjobdata-mcp?

1. Click on "Deploy 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., "@cleanjobdata-mcp search for Python developer jobs in Berlin" 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.

cleanjobdata-mcp

by jhgaylor

Overview Schema Source Related Servers Discussions Admin

Python

Remote

CleanJobData MCP Server

A Model Context Protocol (MCP) server providing tools to interact with the CleanJobData Job API.

PyPI License: MIT

It runs two ways:

stdio (default) — your MCP client launches it locally and it uses the CLEANJOBDATA_API_KEY env var.
HTTP (--transport http) — one hosted server, many users, each authenticating with their own CleanJobData key sent per request. See Running as a remote HTTP server.

Available MCP Interactions

This server exposes the following MCP interactions:

Tools

search_jobs: Search for jobs using the CleanJobData API based on various criteria.
- Parameters: title, sort_by, city_id, state_id, country_id, location, remote, remote_type, company_name, employer_id, salary_min, salary_max, require_salary, experience_level, employment_type, published_after, max_age, include_expired, include_description, limit, cursor, count.
get_job: Retrieve detailed information about a specific job (including its full description) by ID.
- Parameters: job_id.
search_companies: Search for companies by name (fuzzy), website domain, or company IDs.
- Parameters: query, website_url, employer_id, active, limit, offset.
get_company: Retrieve detailed information about a specific company, including enrichment data.
- Parameters: company_id.
suggest_locations: Autocomplete city/state/country names into the IDs used by search_jobs geo filters.
- Parameters: query, kinds, limit.

Prompts

create_candidate_profile: Generates a structured prompt based on candidate details (name, LinkedIn, website, resume text) to help guide job searching.
- Parameters: name, linkedin_url, personal_website, resume_text.

Related MCP server: trackly-cli

Client Setup (Examples: Claude Desktop, Cursor)

To use this server with an MCP client like Claude Desktop or Cursor, you need to configure the client to run the server process and provide the CleanJobData API key.

Ensure uv is installed: curl -LsSf https://astral.sh/uv/install.sh | sh
Obtain a CleanJobData API Key: Request a key from CleanJobData. Set it as the CLEANJOBDATA_API_KEY environment variable.

Configure your client:

Using uvx:
- Claude Desktop: Edit your claude_desktop_config.json:
  { "mcpServers": { "cleanjobdata": { "command": "uvx", "args": [ "cleanjobdata-mcp" ], "env": { "CLEANJOBDATA_API_KEY": "" } } } }
- Cursor: Go to Settings > MCP > Add Server:
  - Mac/Linux Command: uvx cleanjobdata-mcp
  - Windows Command: cmd
  - Windows Args: /c, uvx, cleanjobdata-mcp
  - Set the CLEANJOBDATA_API_KEY environment variable in the appropriate section.

Running from source (Alternative):

Clone the repo and note where you clone it to
Claude Desktop: Edit your claude_desktop_config.json:

{
    "mcpServers": {
        "cleanjobdata": {
            "command": "uv",
            "args": [
                "run",
                "--directory",
                "PATH_TO_REPO",
                "cleanjobdata-mcp"
            ],
            "env": {
                "CLEANJOBDATA_API_KEY": ""
            }
        }
    }
}

Running as a remote HTTP server

The HTTP transport serves many users from a single process. Each request carries its own CleanJobData API key, so the server holds no user credentials and every upstream call is billed to the caller who made it.

cleanjobdata-mcp --transport http --host 0.0.0.0 --port 8000

The MCP endpoint is POST /mcp (streamable HTTP); GET /healthz is an unauthenticated liveness probe.

How clients authenticate

A client sends its key on every request, in either header:

Authorization: Bearer <cleanjobdata-api-key>
X-CleanJobData-API-Key: <cleanjobdata-api-key>

X-CleanJobData-API-Key wins if both are present. A request with neither is rejected with a message telling the caller how to supply one — it does not silently fall back to the server's own key.

Example client config (Claude Desktop / Cursor remote MCP server):

{
  "mcpServers": {
    "cleanjobdata": {
      "url": "https://your-host.example.com/mcp",
      "headers": {
        "Authorization": "Bearer YOUR_CLEANJOBDATA_API_KEY"
      }
    }
  }
}

Or from the command line:

npx mcp-remote https://your-host.example.com/mcp --header "Authorization: Bearer YOUR_KEY"

Docker

Prebuilt images are published to GitHub Container Registry for linux/amd64 and linux/arm64:

docker run --rm -p 8000:8000 ghcr.io/jhgaylor/cleanjobdata-mcp:latest

Tag	Points at
`latest`	The most recent release
`0.2.0`, `0.2`	That specific release / its latest patch
`edge`	The tip of `main`
`sha-<short>`	A specific commit

Or build it yourself:

docker build -t cleanjobdata-mcp .
docker run --rm -p 8000:8000 cleanjobdata-mcp

The image ships no API key — keys arrive per request. It defaults to MCP_TRANSPORT=http, HOST=0.0.0.0, PORT=8000, and runs as a non-root user.

Scaling out

Requests are stateless by default, so you can run several replicas behind a load balancer with no sticky sessions. To use your own ASGI server with multiple workers:

uvicorn cleanjobdata_mcp.app:app --host 0.0.0.0 --port 8000 --workers 4

Pass --stateful (or MCP_STATEFUL=1) only if you need per-session server state; that requires sticky routing.

Single-tenant HTTP deployments

If you want one hosted server that always uses your key rather than the caller's, set both CLEANJOBDATA_API_KEY and CLEANJOBDATA_ALLOW_ENV_KEY_FALLBACK=true. Requests that supply their own key still use it; requests without one fall back to the server's key. Leave this off for anything multi-user — otherwise a user who forgets their header gets billed to you.

CLI options

Flag	Env var	Default	Purpose
`--transport`	`MCP_TRANSPORT`	`stdio`	`stdio` or `http`
`--host`	`HOST`	`127.0.0.1`	Bind address (use `0.0.0.0` in a container)
`--port`	`PORT`	`8000`	Bind port
`--path`	`MCP_PATH`	`/mcp`	URL path of the MCP endpoint
`--json-response`	`MCP_JSON_RESPONSE`	off	Plain JSON instead of SSE, for proxies that buffer
`--stateful`	`MCP_STATEFUL`	off	Keep per-session state in memory
`--allowed-host`	`MCP_ALLOWED_HOSTS`	none	Allowed `Host` values; setting any enables DNS-rebinding protection
`--allowed-origin`	`MCP_ALLOWED_ORIGINS`	none	Allowed `Origin` values

Operational notes

Terminate TLS in front of the server (load balancer, reverse proxy, or platform ingress). Keys travel in request headers, so plain HTTP over the public internet would expose them.
Tool handlers run in a thread pool, so a slow upstream call blocks one thread rather than the whole event loop. Very high concurrency benefits from more replicas rather than one large process.

Development

This project uses:

uv for dependency management and virtual environments
ruff for linting and formatting
hatch as the build backend

Common Tasks

# Setup virtual env
uv venv

# Install dependencies
uv pip install -e .

# install cli tools
uv tool install ruff

# Run linting
ruff check .

# Format code
ruff format .

Environment Variables

CLEANJOBDATA_API_KEY: Your API key for the CleanJobData API, sent upstream as a Bearer token. Required for stdio; over HTTP the caller's own header supplies the key instead.
CLEANJOBDATA_ALLOW_ENV_KEY_FALLBACK: Set to true to let HTTP requests without a key fall back to CLEANJOBDATA_API_KEY. Off by default — see Single-tenant HTTP deployments.
CLEANJOBDATA_API_BASE: Override the API base URL (default https://api.cleanjobdata.com).

Transport settings (MCP_TRANSPORT, HOST, PORT, …) are listed under CLI options.

Testing

This project uses pytest for testing the core tool logic. Tests mock external API calls using unittest.mock.

Install test dependencies:

# Ensure you are in your activated virtual environment (.venv)
uv pip install -e '.[test]'

Run tests:

pytest

Contributing

Contributions are welcome.

License

This project is licensed under the MIT License - see the LICENSE file for details.

Available Tools

5 tools

get_companyA

Get detailed information about a specific company, including enrichment data

Args: company_id: The unique identifier of the company (employer_id)

ParametersJSON Schema

Name	Required	Description	Default
`company_id`	Yes

Output Schema

ParametersJSON Schema

Name	Required	Description
`result`	Yes

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 burden of behavioral disclosure. 'Get' implies a read-only operation, and 'enrichment data' hints at additional information, but no details on caching, permissions, or error behavior are provided. This is minimally transparent but not misleading.

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 a single sentence followed by a one-line argument explanation. Every word earns its place, and the main purpose 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 the tool has only one parameter and an output schema exists, the description is sufficiently complete. It explains the core function and the parameter, though 'enrichment data' is vague. It covers what is needed for a simple lookup tool.

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 schema only says 'Company Id' (type string), while the description adds 'The unique identifier of the company (employer_id)' which clarifies the semantic meaning. Since schema coverage is 0%, the description compensates well for the single required parameter.

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 'Get detailed information about a specific company, including enrichment data', which is a specific verb+resource. It distinguishes itself from sibling 'search_companies' by focusing on retrieving one known company rather than searching.

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 when a specific company_id is known, but does not explicitly state when to use this tool versus alternatives like search_companies. It provides clear context but lacks explicit exclusion or alternative guidance.

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

get_jobA

Get detailed information about a specific job, including its full description

Args: job_id: The unique numeric identifier of the job

ParametersJSON Schema

Name	Required	Description	Default
`job_id`	Yes

Output Schema

ParametersJSON Schema

Name	Required	Description
`result`	Yes

TDQS

A4/5.0

Behavior3/5

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

With no annotations, the description must carry the transparency burden. It discloses that the return includes the job's full description, but it does not mention other behavioral aspects such as read-only status, auth requirements, rate limits, or potential errors. For a simple getter, this is adequate but not exhaustive.

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 highly concise: one sentence stating the purpose, followed by a brief Args section. The main purpose is front-loaded, and every word earns its place. No unnecessary repetition or fluff.

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's simplicity (one parameter, clear purpose) and the presence of an output schema, the description is sufficiently complete. It covers what the tool does and the parameter. It does not address error cases or non-usage scenarios, but these are less critical for a single-job retrieval tool.

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 description explains that job_id is 'the unique numeric identifier of the job,' adding semantic meaning beyond the schema's type integer and title. This clarifies the purpose and uniqueness of the parameter, which is the only parameter. The added meaning compensates for the empty schema description.

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 states 'Get detailed information about a specific job, including its full description,' which clearly identifies the verb (get), the resource (job), and the scope (specific job by ID). The explicit mention of 'full description' adds specificity and distinguishes it from search_jobs, which is a search/filter operation.

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 retrieving a specific job, but it does not explicitly state when to use this tool over search_jobs or provide exclusions or prerequisites. The context is clear enough for basic use, but guidance on when not to use it is missing.

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

search_companiesA

Search for companies using the CleanJobData API

query, website_url, and employer_id are mutually exclusive lookup modes, checked in priority order: employer_id, then website_url, then query.

Args: query: Company name to search for (fuzzy match, ranked by relevance) website_url: Match by registrable domain; accepts a bare domain or full URL employer_id: Look up one or more companies directly by ID (max 100) active: Only return companies with active jobs (default true) limit: Results per request (max 100 when searching) offset: Skip this many rows

ParametersJSON Schema

Name	Required	Description	Default
`limit`	No
`query`	No
`active`	No
`offset`	No
`employer_id`	No
`website_url`	No

Output Schema

ParametersJSON Schema

Name	Required	Description
`result`	Yes

TDQS

A4.7/5.0

Behavior5/5

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

With no annotations provided, the description takes full responsibility for behavioral disclosure. It reveals fuzzy matching, relevance-ranked results, a default for active (true), limits, and offset behavior, offering rich insight beyond the raw schema.

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 well-structured with a summary line and an Args list, and every sentence adds valuable detail. It is slightly verbose due to explaining mode interactions, but this is necessary for correct tool usage.

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 an output schema exists, return format details are unnecessary. The description covers all six parameters, mode priority, defaults, constraints, and search behavior, making it complete for an agent to select and invoke the tool correctly.

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

Parameters5/5

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

The input schema has no parameter descriptions (0% coverage), but the description's Args section thoroughly explains every parameter, including mutual exclusivity, accepted formats, defaults, and max values, fully compensating for the schema's silence.

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 'Search for companies using the CleanJobData API' and enumerates three distinct lookup modes (query, website_url, employer_id), making the tool's purpose specific and distinguishable from job-focused siblings.

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?

It explicitly explains that query, website_url, and employer_id are mutually exclusive and checked in priority order, providing clear guidance on when to use each mode. However, it does not directly compare this tool with sibling tools like get_company or search_jobs.

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

search_jobsA

Search for jobs using the CleanJobData API

Results are paginated with opaque cursors: pass the response's pagination.next_page (or prev_page) token back as cursor to move through pages.

Args: title: Full-text search on job title / keywords sort_by: Sort order: "published" (default) or "relevance" (requires title) city_id: City IDs to filter by (use suggest_locations to find IDs) state_id: State IDs to filter by (use suggest_locations to find IDs) country_id: Country IDs to filter by (use suggest_locations to find IDs) location: ISO 3166-1 alpha-2 country codes (e.g. ["US", "DE"]); used when no city/state/country IDs are provided remote: True to return remote-only jobs remote_type: One of fully_remote, remote_country, remote_region, hybrid company_name: Substring match on company name employer_id: Company IDs to filter by (max 100) salary_min: Minimum salary for the salary range filter salary_max: Maximum salary for the salary range filter require_salary: True to only return jobs with a verified salary experience_level: Experience levels: EN (entry), MI (mid), SE (senior), EX (executive) employment_type: Employment types: FULL_TIME, PART_TIME, CONTRACT, INTERN, TEMPORARY, FREELANCE, APPRENTICESHIP, VOLUNTEER, PER_DIEM, OTHER published_after: Only jobs published at or after this ISO 8601 instant max_age: Rolling window on published date, integer with optional unit h/d/w (e.g. "7d") include_expired: True to also include closed/expired listings include_description: True to include the full HTML job description (excluded from list results by default) limit: Results per request (1-100) cursor: Opaque pagination token from a previous response count: True to include the total job count in pagination (costs an extra query)

ParametersJSON Schema

Name	Required	Description	Default
`count`	No
`limit`	No
`title`	No
`cursor`	No
`remote`	No
`city_id`	No
`max_age`	No
`sort_by`	No
`location`	No
`state_id`	No
`country_id`	No
`salary_max`	No
`salary_min`	No
`employer_id`	No
`remote_type`	No
`company_name`	No
`require_salary`	No
`employment_type`	No
`include_expired`	No
`published_after`	No
`experience_level`	No
`include_description`	No

Output Schema

ParametersJSON Schema

Name	Required	Description
`result`	Yes

TDQS

A4.4/5.0

Behavior4/5

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

With no annotations, the description carries the burden of behavioral disclosure. It covers pagination cursors, default limit/count behavior, the extra query cost of count=true, and include_description being excluded by default. It does not mention auth/rate limits, but these are not critical for a read-only search, and the output schema covers return shape.

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 front-loaded with a one-sentence purpose, then a concise pagination note, then a clear bulleted arg list. For a tool with 22 parameters, it is well-organized and every line provides necessary information without filler.

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?

For a complex 22-parameter search tool with no annotations and no schema descriptions, the description is highly complete. It explains pagination, parameter dependencies, defaults, and behavioral caveats. Combined with the output schema, an agent has enough information to invoke search_jobs correctly.

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

Parameters5/5

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

Schema description coverage is 0%, so the description must fully compensate. It documents all 22 parameters with specific meanings, allowed enum values (remote_type, experience_level, employment_type), syntax for max_age, and semantic details like location being used only when no IDs are provided. This goes far beyond the raw 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?

The description opens with 'Search for jobs using the CleanJobData API,' which clearly states the verb ('search') and the resource ('jobs'). It is distinct from siblings like get_job (fetching a single job) and search_companies (searching companies), so an agent can easily differentiate when to select this tool.

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?

While the description provides useful usage context (e.g., pagination cursor flow, suggest_locations for IDs, and sort_by requiring title), it does not explicitly compare against alternatives or state when not to use search_jobs versus get_job or search_companies. The appropriate use is implied rather than directly contrasted.

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

suggest_locationsA

Look up city/state/country IDs by name for use in search_jobs filters

Args: query: The search query (e.g. a city, state, or country name) kinds: Location types to include: city, state, country (default all) limit: Maximum results to return (1-30)

ParametersJSON Schema

Name	Required	Description	Default
`kinds`	No
`limit`	No
`query`	Yes

TDQS

A4.3/5.0

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 accurately describes a read-only lookup operation and the purpose, but does not disclose behaviors such as response format, error handling, or edge cases (e.g., no matches). It is not misleading, but it lacks depth beyond the basic action and parameters.

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 compact and well-structured: a one-sentence purpose followed by a clear argument list. Every line earns its place, with no redundant information or fluff.

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's simplicity (3 parameters, no output schema, no annotations), the description covers the essential context: purpose, relationship to search_jobs, and parameter details. It does not explicitly describe the return value format, but for a location ID lookup the purpose implies the return type. Overall, it is sufficiently complete for an AI agent to select and invoke the tool; a small margin for improvement remains.

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

Parameters5/5

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

Schema description coverage is 0%, so the description fully compensates by clearly explaining each parameter: 'query' (search query with examples), 'kinds' (location types, default all), and 'limit' (max results, 1-30). It adds value beyond the schema, including defaults and constraints.

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's function: 'Look up city/state/country IDs by name for use in search_jobs filters.' It uses a specific verb ('look up'), identifies the resource (location IDs), and explicitly ties it to a sibling tool (search_jobs), distinguishing it from the other search/retrieval tools.

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 provides clear usage context by stating the purpose is 'for use in search_jobs filters.' This implies when to use the tool (before calling search_jobs with location filters). However, it does not explicitly mention alternatives or when not to use it, though the sibling tools are obviously different in scope.

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.

5 tool updatesv0.1.0Aug 5, 2026
- First observedget_company
- First observedget_job
- First observedsearch_companies
- First observedsearch_jobs
- First observedsuggest_locations

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

A4.4/5.0

Scored 2026-08-05 10:20 across 5 tools

Disambiguation5/5

Each tool has a distinct purpose: searching jobs, retrieving job details, retrieving company details, searching companies, and suggesting location filters. No two tools overlap in functionality, making selection unambiguous.

Naming Consistency5/5

All tool names follow a consistent verb_noun pattern with snake_case: search_jobs, get_job, get_company, search_companies, suggest_locations. The naming is predictable and clearly indicates the action and resource.

Tool Count5/5

Five tools is well-scoped for a job search API. Each tool covers a core operation (search, detail retrieval, and location lookup) without redundancy or unnecessary bloat.

Completeness5/5

For a read-only job search service, the tool surface covers all necessary workflows: finding jobs, inspecting job details, finding companies, inspecting company details, and resolving location IDs for filtering. There are no obvious gaps that would hinder an agent.

Maintenance

ActivitySlowing

ResponsivenessNo issues

Resources

Need Help?

Related Servers

Related MCP Connectors

nü people Job Server A
io.github.nu-people
Public MCP server for discovering open jobs. Search, filter, and get application links.
Search
52
getjobzi-mcp
io.github.getjobzi
GetJobzi MCP server for job search, application tracking, and career forecasting.
Search AI & Machine Learning
2
WeJob B
ch.wejob
Read-only MCP server for public WeJob jobs, formations, and companies.
Search Open Data
821
UnifAPIOAuth
com.unifapi
Hosted MCP server for live public-data APIs and Skills for AI agents.
Open Data Search AI & Machine Learning
2

Related MCP Servers

job-search-mcp
Search Web Scraping
VincenzoImp
A
license
Not graded
quality
A
maintenance
MCP server that exposes job search data from multiple boards, enabling clients to query and manage job listings via natural language.
Updated 2 days ago (2026-09-19 00:35 UTC)
7
MIT
trackly-cliofficial
Search CRM Project Management
trackly-app
A
license
Not graded
quality
A
maintenance
MCP server for job search and application tracking, enabling AI agents to search jobs, get details, manage applications, and find contacts across 128K+ jobs and 1,900+ companies.
Updated 2 days ago (2026-09-19 16:11 UTC)
396 npm
3
MIT
bach-jsearchofficial
Search Research & Data
BACH-AI-Tools
A
license
A
quality
D
maintenance
MCP server for accessing Jsearch API to search jobs, get job details, and retrieve salary estimates.
Updated 9 months ago (2025-12-07 20:03 UTC)
4
MIT
job-search-mcp
Search Email Autonomous Agents
OmriH-Elister
A
license
Not graded
quality
C
maintenance
An MCP server that exposes job-search and application-management capabilities to compatible AI clients, enabling discovery of vacancies, drafting of tailored application materials, and coordinated human-approved submissions.
Updated a month ago (2026-08-24 16:24 UTC)
MIT

CleanJobData MCP Server

Available MCP Interactions

Tools

Prompts

Client Setup (Examples: Claude Desktop, Cursor)

Running as a remote HTTP server

How clients authenticate

Docker

Scaling out

Single-tenant HTTP deployments

CLI options

Operational notes

Development

Common Tasks

Environment Variables

Testing

Contributing

License

Available Tools

Output Schema

Output Schema

Output Schema

Output Schema

Tool Schema Changelog

Maintenance

Resources

Related MCP Connectors

Related MCP Servers

trackly-cliofficial

bach-jsearchofficial