Dice

Name: Dice MCP Server
Availability: InStock
Author: Dice

Productivity3 toolsNo Auth Required

Search Dice's tech job listings from your AI agent, then pull a full job description or the hiring company's profile. 3 read-only tools, no sign-in, and the directory only lists one of them.

Verified connector

Listed by Anthropic as a partner connector in its Connectors Directory.

Connection checked by Agentman on 18 August 2026.

Anthropic states this reflects the level of review a connector received, not a security audit.

Connect Dice via MCP

https://mcp.dice.com/mcp

Works in any MCP-compatible client. In Agentman Studio it is one click — no config file to edit.

Dice Tools & Capabilities (3)

search_jobsRead-only

Search for job listings by keyword, location, and filters. Returns job details, company info, and application links. Use this tool when users want to find jobs, search employment opportunities, or explore job openings. DO NOT use for: applying to jobs, submitting applications, or making employment decisions. LLM USAGE INSTRUCTIONS: - ALWAYS provide the keyword parameter (required) - When presenting results to users, include BOTH the job details URL (detailsPageUrl) AND the company page URL (companyPageUrl) for each job - Use location to find geographically relevant positions - Combine filters to refine searches (e.g., workplace_types=['Remote'] for remote work) - Use posted_date to find recent openings ('ONE'=1 day, 'THREE'=3 days, 'SEVEN'=7 days) - Default jobs_per_page is reasonable, increase for comprehensive searches - Use company_name to scope results to a specific employer - Use sort='datePosted' when the user wants the newest listings instead of the most relevant - Use facets to get aggregate counts (e.g., how many results are remote vs on-site) without paging through all results - After presenting results, do NOT automatically call get_job_details for every job returned. Wait for the user to indicate which specific job(s) they're interested in, then pass that job's guid to get_job_details. IMPORTANT - AI DISCLOSURE REQUIREMENT: When presenting job search results to users, you MUST include an appropriate disclosure that these results were retrieved using AI assistance. Example disclosure language: "These job listings were found using AI-powered search. Please review all job details carefully and verify information directly with employers before applying." This tool provides job listing data only. Final employment decisions should always involve human judgment and direct review of complete job postings. Args: keyword: The job keyword or title to search for (required) location: Geographic location for the job search (city, state, country) radius: Search radius from the specified location (minimum 1, requires radius_unit) radius_unit: Unit for search radius. Options: 'mi', 'km' (requires radius) jobs_per_page: Number of jobs to return per page (1-100, defaults to 5) page_number: Page number for pagination (1-based, default is 1) sort: Sort order for results. Options: 'relevance', 'datePosted' (defaults to relevance) posted_date: Filter by posting date. Options: 'ONE' (1 day), 'THREE' (3 days), 'SEVEN' (7 days) workplace_types: Workplace arrangements. Options: 'Remote', 'On-Site', 'Hybrid' employment_types: Employment types. Options: 'FULLTIME', 'CONTRACTS', 'PARTTIME', 'THIRD_PARTY', 'INTERNSHIP' employer_types: Employer types. Options: 'Direct Hire', 'Recruiter', 'Other' willing_to_sponsor: Filter for employers willing to sponsor work authorization (boolean) easy_apply: Filter for jobs with easy application process (boolean) company_name: Filter by company name fields: Specific fields to include in response (optional, returns all exposed fields by default) facets: Facet dimensions to aggregate (optional). Options: 'employmentType', 'postedDate', 'workFromHomeAvailability', 'workplaceTypes', 'employerType', 'easyApply', 'isRemote', 'willingToSponsor' Returns: JobSearchResult: Contains: - data: List of JobDisplayFields with job details including: * guid: The job's identifier to pass as job_id to get_job_details for the full description and skills list (NOT the `id` field, which is a different, internal identifier not accepted by get_job_details) * detailsPageUrl: Direct link to full job posting * companyPageUrl: Link to company profile page * title, summary, salary, location, employmentType, etc. - metadata: Search metadata with pagination info and facet results Raises: Exception: If API call fails or input validation errors occur

get_job_detailsRead-only

Retrieve a job's full description and associated skills by job ID. Use this tool when users want more detail about a specific job than search_jobs returns (e.g. after finding a job via search_jobs and wanting its full description and skills list). DO NOT use for: searching/discovering jobs by keyword (use search_jobs instead). LLM USAGE INSTRUCTIONS: - Only call this after the user has picked out a specific job from search_jobs results (or otherwise supplied a job's guid directly) — do not call it speculatively for every search result. - After returning job details, do NOT automatically call get_company. Instead, offer to look up the company (e.g. "Want me to pull up more info on the company?") and only call get_company, passing this same job_id, if the user says yes. Args: job_id: The unique identifier of the job to retrieve (required). This must be the job's `guid` field from a search_jobs result, NOT its `id` field — `id` is a different, internal identifier that this tool does not accept. Returns: JobDetails: Contains: - description: The full job description - skills: List of Skill objects associated with the job Raises: Exception: If the API call fails, the job is not found, or input validation errors occur

get_companyRead-only

Retrieve the name and description of the company behind a job, by job ID. Use this tool when users want more detail about a company than search_jobs/get_job_details return (e.g. after finding a job and wanting to know more about the company that posted it). DO NOT use for: searching/discovering companies or jobs by keyword (use search_jobs instead). LLM USAGE INSTRUCTIONS: - The typical flow is: search_jobs to find jobs -> user picks one -> offer to look up the company -> if the user agrees, call this tool with that same job_id (the same guid used for get_job_details; no separate lookup step is needed first). - Do not call this automatically right after get_job_details; ask the user first unless they already explicitly asked for company details. - Not every company has published an employer branding profile, and some profiles are marked not visible by the company. When that happens this tool does NOT raise — it returns a Company with `message` set and empty name/desc. Relay that message to the user (e.g. "Looks like that company hasn't published a public profile.") rather than treating it as an error. Args: job_id: The unique identifier of the job whose company to look up (required). This must be the job's `guid` field from a search_jobs result, NOT its `id` field — `id` is a different, internal identifier that this tool does not accept. Returns: Company: Contains: - name: The company name (empty if message is set) - desc: The company description (empty if message is set) - message: Set instead of name/desc when there is no visible company profile to show; None when name/desc are populated Raises: Exception: If the job is not found, an API call itself fails (network error, non-200 response, GraphQL errors), or input validation errors occur

Read from the server on 2026-08-18, including each tool's own safety annotations.

Limits

It cannot apply to anything. All three tools are read-only, no schema accepts a resume or profile, and search_jobs explicitly instructs the model not to use it for applications or employment decisions. Applying happens on the Dice site through the returned link.
There is no company lookup. get_company is keyed by job_id, so an employer with no live posting is invisible to this connector. There is no company search tool of any kind.
You cannot search by anything but keyword. keyword is the only required parameter and the only free-text query field; there is no semantic search, no resume matching and no "jobs like this one" tool.
Dice publishes no numeric rate limit, but confirms limits exist by documenting HTTP 429 and advising exponential backoff at one, two and four seconds plus result caching. Make no assumption about headroom.
Coverage is Dice's job board and nothing else. Every result comes from Dice's own listings. A role advertised only on a company careers page or another board will not appear, and the connector cannot tell you that it is missing.
The results are employer-supplied and unvetted. Dice's Terms state the site is only a venue for employers to post opportunities, that it does not evaluate or censor job listings except as required by law, and that it makes no guarantees as to the site's completeness or correctness. Salary, sponsorship and remote flags are what the employer entered.
The service is provided "as is". Dice's Terms disclaim all warranties including fitness for purpose, and state you assume total responsibility and risk for your use and your reliance on it.
Dice's Terms prohibit using site output to train AI models. The Code of Conduct forbids using information obtained from the site to directly or indirectly create, train, test or improve any machine learning, large language or AI model, including for research and non-commercial use. Using the connector to answer a question is the sanctioned use; retaining its output as training material is not.
No prompts or resources today. Both capabilities are declared and both lists are empty, so there is nothing to invoke and no context to attach.
The server reports two different versions of itself. Its root path reports version 1.0.0 and its health endpoint reports 1.0.2, so neither is a reliable thing to pin behaviour to.

Frequently asked questions

Does the Dice MCP server need a Dice account or sign-in?

No. We opened an anonymous handshake against the endpoint on 2026-08-18 and the server returned all three tool definitions without any credential, and Dice's own documentation states no authentication is required for basic usage. There is no OAuth flow, no API key field and no account parameter on any tool. You do need a Dice account to actually apply to a job, but that happens on the website.

Why does the directory only list one Dice tool?

Because Anthropic's listing is incomplete rather than out of date in the usual direction. The directory snapshot of 2026-08-16 names only search_jobs, while the live handshake on 2026-08-18 returns three tools. The two extras, get_job_details and get_company, are absent from the published listing but answer normally on the server. Dice's own documentation also describes only the search tool.

Why does get_company take a job ID instead of a company ID?

Because the connector has no company index to look up. Its schema requires job_id and nothing else, so a company is only reachable through a job that company posted. There is no search-by-company-name tool and no company identifier anywhere in the surface. If you want a specific employer, you search jobs filtered to their name first, then pass a result's identifier.

Can the Dice connector apply to jobs on my behalf?

No. All three tools are annotated readOnlyHint true and destructiveHint false, and the search tool's own description tells the model not to use it for applying, submitting applications or making employment decisions. Nothing in any schema accepts a resume, a cover letter or a profile. Applying is a manual step you take on the Dice website through the link the connector returns.

Which job identifier do I pass to get_job_details?

The guid field from a search result, not the id field. Both tools state this explicitly in their descriptions and warn that id is a different internal identifier they will not accept. The two fields sit side by side in every search result, so this is the easiest mistake to make with this connector and the one most likely to look like a broken server.

Does the Dice MCP server offer prompts or resources?

It declares both capabilities and serves neither. The initialize response on 2026-08-18 advertised prompts and resources with listChanged true, yet prompts/list, resources/list and resources/templates/list each returned an empty array. That is different from a server that does not implement the methods at all, and it means the surface may fill in later without the capability block changing.

Are there rate limits on the Dice MCP server?

Dice does not publish a numeric ceiling, but its documentation confirms limits exist by naming HTTP 429 as a condition you can hit. The vendor's advice is to reduce request frequency, implement exponential backoff at one, two and four seconds, and cache results to avoid duplicate requests. Treat page sizes conservatively; the tool accepts up to 100 results per page.

Sources

Live initialize, tools/list, prompts/list, resources/list and resources/templates/list against https://mcp.dice.com/mcp — 2026-08-18. Read-only throughout: no tool was ever called, so no search was run and no job or company data was fetched. · retrieved 2026-08-18
Dice — Dice MCP Documentation — https://www.dice.com/about/mcp (fetched 2026-08-18). This is the exact documentation URL Anthropic's directory publishes for this connector, and www.dice.com/robots.txt does not disallow the /about/ path. · retrieved 2026-08-18
Dice — service root and /health on the endpoint host, both returning JSON without authentication (fetched 2026-08-18) · retrieved 2026-08-18
Dice — Terms & Conditions — https://www.dice.com/about/terms-and-conditions (fetched 2026-08-18) · retrieved 2026-08-18
Dice — Privacy Policy — https://www.dice.com/about/privacy-policy (fetched 2026-08-18) · retrieved 2026-08-18
Anthropic connector directory — https://claude.ai/directory/3035842b-464b-45f0-b8f0-1ddc01fb2eb2 (snapshot 2026-08-16) · retrieved 2026-08-16