Skip to main content
Glama

Hyreflow

Server Details

Recruitment automation: source, enrich, qualify and sequence candidates, push to your ATS.

Ownership verified
Status
Healthy
Uptime
100.0% over the last 24 hours
OAuth
Works in Glama
Last Tested
Transport
Streamable HTTP · MCP 2025-11-25
URL
Repository
automindz-solutions/hyreflow-plugins
GitHub Stars
1
ChatGPT
–
Claude
–

TDQS

A3.7/5.0

Scored across 28 tools

Disambiguation4/5

Most tools map to a distinct resource+action (billing, datasets, knowledge, workflows, tools catalog), and descriptions clarify boundaries well. A few pairs overlap: hyreflow_enrich_run vs hyreflow_tools_execute's row-batch mode, and hyreflow_skill_read vs hyreflow_custom_skill_read, which an agent could plausibly confuse.

Naming Consistency4/5

Nearly all names follow a hyreflow_<resource>_<action> snake_case pattern, which is predictable and readable. Minor deviations: singular/plural drift (hyreflow_workflow_run, hyreflow_workflow_runs, hyreflow_workflows_list) and a few verb-first names (hyreflow_extract_image, hyreflow_shortlist, hyreflow_onboarding).

Tool Count3/5

28 tools is on the heavy side and pushes past the comfortable 3-15 range, with several near-sibling tools (three skill tools, three dataset tools, three knowledge-read variants). The breadth is genuine — skills, datasets, knowledge base, provider tools, workflows, billing — so each tool has a home, but the surface is larger than an agent can hold comfortably.

Completeness4/5

Coverage is broad: full knowledge CRUD plus search/import, custom skill create/read/list, dataset list/read/export, enrichment with async job polling, and tool discovery/describe/execute. Gaps are minor but real: no workflow create/update/delete (only list and run), and no delete for datasets or custom skills.

Available Tools

28 tools
hyreflow_billing_balanceA
Read-only
Inspect

Spendable credits and recent spend in this workspace. For anyone but the owner the spend and recent calls are their own (scope: "member"), and under a spend cap the balance is their allowance. Free.

hyreflow_custom_skill_readA
Read-only
Inspect

Return one custom skill's files ({path: text}) at its live version, with its version history. version reads another version, such as a draft still waiting for the workspace owner. Free.

Inputs: skill_id (required), version.

hyreflow_custom_skill_saveAInspect

Create a custom skill, or save a new version of one. files is the whole package as {path: text} with a SKILL.md whose frontmatter has a name and a one-line description; text files only. Without skill_id it creates a skill of scope personal (only the caller sees it) or org (the whole team). With skill_id it saves a new version and keeps every earlier one. A personal version is live at once. A team version waits for the workspace owner to approve it in the Hyreflow dashboard, unless the caller is the owner. Free.

Inputs: files (required), scope, skill_id.

hyreflow_custom_skills_listA
Read-only
Inspect

List the skills this workspace's people wrote themselves: the caller's personal skills and the team's skills. Each entry has id, name, description, scope (personal or org), live_version and pending_version. Free.

hyreflow_dataset_exportAInspect

Create a download link for a dataset's full CSV (ds_…): every row and every column, not a sample. The link opens in the browser signed in to Hyreflow; the response's instruction field explains what to do if the page asks to sign in or cannot find the dataset. Free.

Inputs: dataset_id (required).

hyreflow_dataset_readA
Read-only
Inspect

Read a page of rows from a stored dataset (ds_…): at most 100 rows per call (default 25), paged with offset. The reply carries has_more and next_offset. format is json (default, row objects) or csv (the same rows as one CSV string, identical cells to the exported file and far fewer tokens). columns returns only those fields, named by key or dotted path into nested rows (e.g. ["attributes.title","attributes.first_seen_at"]), and raises the page cap to 500 rows; a path a row lacks reads as null. Any page stops early at about 60,000 characters (then limit is the rows served and next_offset resumes the read). A dataset another workspace owns reads as 'dataset not found'. Free.

Inputs: dataset_id (required), limit, format, offset, +1 more.

hyreflow_datasets_listA
Read-only
Inspect

List this workspace's stored datasets (ds_…), newest first. Any search or enrichment over 50 rows, and every workflow run's output, is stored as a dataset; the original response carries only a 5-row sample. Each entry has id, name, source, row_count and created_at. session_id narrows the list to one session; without it the whole workspace is listed. Free.

Inputs: limit, offset, session_id.

hyreflow_enrich_jobA
Read-only
Inspect

Fetch an async enrichment job by its job id (the job handle on a still_enriching row). Returns status (pending | settled | failed | expired), credits charged, the email when settled, and the result. A still_enriching row is NOT a miss: its job usually settles within 1-2 minutes, so a pending status means check again later. A job that settles with no email skipped the chain's later providers for that row. Free.

Inputs: job_id (required), provider.

hyreflow_enrich_runA
Destructive
Inspect

Run ordered enrichment steps over a list of rows, each row independently (the CSV-style, per-column executor). Returns a summary with a cost estimate, not raw rows. Rows come from rows, or from a stored dataset via input (its ds_ id), in which case the whole dataset is enriched into a NEW dataset (_meta.dataset_id). Enrichment adds data only; it does not screen or filter rows. The call waits about 20s: a longer run returns _meta.status: "running" and a run_id, and a call with only run_id returns its progress at no charge. A row still processing at the provider reads still_enriching, which ends that row's chain, and carries a job_id, a resume {tool, method, id_arg} and, when fetchable, a job {provider, job_id} handle. A still_enriching row is NOT a miss: its email is still being fetched and usually arrives within 1-2 minutes. _meta.pending counts such rows and _meta.instruction says how to re-check them (free) every _meta.poll_after_s seconds until _meta.pending is 0. Resending an identical run within 15 minutes returns the first one, charged 0. The quote's expected_credits is the typical cost; total_max_credits the worst case.

Inputs: user_prompt (required), rows, input, steps, +4 more.

hyreflow_extract_imageA
Read-only
Inspect

Put candidate profile photos into a hyreflow artifact page, which can't load images from other sites. Pass dataset_id when the rows came from a dataset (the engine reads every row's photo_url, or a raw AI Ark row's profile.picture.source, itself, up to 500), otherwise urls: the AI Ark and LinkedIn photo links, up to 100. The photos are shrunk and kept for 15 minutes. Returns apply_url: post the finished page to it and get the page back with the photos inside (instruction has the command). skipped counts the links that couldn't be fetched, by reason; those people show initials. Call it only when the user wants photos. Free.

Inputs: urls, dataset_id.

hyreflow_feedbackAInspect

Send feedback or a bug report to the Hyreflow team. Files a tracked issue that people on the team read, and returns its URL. A submission cannot be withdrawn. Free.

Inputs: message (required), kind, repro_query.

hyreflow_knowledge_importAInspect

Add text files from the user's own computer to this workspace's second brain as draft notes in the Imported folder, one note per file, up to 50 files per call. Each file has a name and its content, and may have a kind (icp, persona, offer, pitch, proof, other) and up to 20 tags. A file with no text is skipped, a body over 64 KB is cut and marked truncated, a file already imported with the same name and text is skipped, so resending a call adds nothing, and a note that already exists is left as it is: a slug taken gets a numeric suffix. Send only files the user has seen listed and approved: every member's agent reads the notes. Returns the notes written and the files skipped with a reason. Free.

Inputs: files (required).

hyreflow_knowledge_indexA
Read-only
Inspect

List every page of this workspace's second brain, the notes Hyreflow keeps about the business (roles, ideal customer, messaging). Each entry has slug, title, type, folder, status, tags and updated_at, without the page text. build is the state of the latest build (running, done or failed) and null when none started. Empty when no brain has been built. Persona Search filter pages hold the titles, locations, skills, keywords and seniority for a people search with the provider tools. Folders by task: Candidate personas, Search filters and Pains for sourcing, Angles, Pains, Triggers and Proof for outreach, Client ICP, Client personas, Offers and Desks for BD. Free.

hyreflow_knowledge_readA
Read-only
Inspect

Read one page of this workspace's second brain by slug. view body (default) returns the title and text. full adds data, sources, the pages it links to, the pages that link to it and the link targets that match no page. Persona Search filter pages hold the titles, locations, skills, keywords and seniority for a people search with the provider tools. Free.

Inputs: slug (required), view.

hyreflow_knowledge_writeA
Destructive
Inspect

Create or change one note in this workspace's second brain. With an existing slug only the fields given change, and its sources stay. Without one, title is required and the slug comes from it, and a slug already taken is refused rather than replaced. status archived takes a note out of search. Every member's agent reads the change at once and there is no undo, so a note is saved only when the user asked for it or said yes to its exact text, and a note the build wrote is changed only when the user asks. A note holds facts about the agency and its clients, not about a named person. Free.

Inputs: body, slug, tags, title, +2 more.

hyreflow_onboardingAInspect

Run Hyreflow onboarding for the signed-in person. The default step 'start' returns the onboarding instructions to follow and moves the Hyreflow setup page on. Call again with step 'progress' and a short note while working, and step 'completed' at the end. Repeat calls are harmless. Free.

Inputs: note, step.

hyreflow_onet_lookupA
Read-only
Inspect

Resolve a job title to O*NET-SOC occupation codes, each with its official title and description. Matches marked loose ('rank dropped', 'root word') are approximate. The predictleads discover_job_openings method requires these codes as onet_codes. Free.

Inputs: title (required), limit.

hyreflow_shortlistA
Destructive
Inspect

Bulk-screen candidates against a job description: one structured decision per candidate, ranked by tier then score, with a tier (tier_1 | tier_2 | no_fit | insufficient_data | unscored) and per-category scores. Takes job_spec plus either candidates (up to 1000 row objects, e.g. what a CRM/ATS search returned) or input (a ds_ dataset id, for a larger pool). Rows need work history; a pool of sourcing stubs without it is refused. The question set is generated from the job spec once and reused for every later screen of it. The call waits about 20s: a finished screen returns the top 25 ranked rows (name, row, shortlist cell); an unfinished one (including every first screen of a new job spec, which also writes its questions) returns {run_id, status, progress, poll_after_s}, and a call with only run_id returns the ranking once ready, at no charge. Every row, full profile included, is stored in the dataset at _meta.dataset_id. Resending an identical screen within 15 minutes returns the first one, charged 0. dry_run: true quotes the cost without running. Charges credits.

Inputs: user_prompt (required), input, run_id, dry_run, +10 more.

hyreflow_skill_readA
Read-only
Inspect

Return one skill document in full. skill is the package name (e.g. 'hyreflow-recruit') and alone returns its SKILL.md; path selects a document inside it (e.g. 'provider-playbooks/apollo.md'), or takes a hyreflow://skills/ URI whole. Free.

Inputs: skill (required), path.

hyreflow_skills_listA
Read-only
Inspect

List the Hyreflow skill documents: recruiting playbooks, one provider playbook per vendor (access rules, payload shapes, known limits), pipeline recipes and sub-agent prompts. Free.

hyreflow_tools_describeA
Read-only
Inspect

Describe one Hyreflow tool and its methods, or one method in full: expected payload, credit cost, usage notes, and the skill document that covers it. Free.

Inputs: tool (required), method.

hyreflow_tools_executeA
Destructive
Inspect

Execute a Hyreflow tool method against live data providers. Charges credits at the described cost; dry_run: true returns a quote without running. Waterfall tools such as people_search take only payload. Enrichment waterfalls (email_enrichment, personal_email, linkedin_profile, phone_enrichment) also accept rows: up to 100 row objects enriched in one call, in place of payload and method. A row still processing at the provider comes back as still_enriching with a job_id, a resume {tool, method, id_arg} and, when the job is fetchable, a job {provider, job_id} handle. A still_enriching row is NOT a miss: its email is still being fetched and usually arrives within 1-2 minutes. _meta.pending counts such rows and _meta.instruction says how to re-check them (free) every _meta.poll_after_s seconds until _meta.pending is 0. A multi-row call stores its rows in a dataset (_meta.dataset_id), and a pending row completes in that dataset when its job finishes. Resending identical rows within about 15 minutes returns the first call's dataset at no charge (_meta.replayed); resending one pending row's payload starts and bills a new job. A call above the workspace's confirmation threshold returns confirmation_required with a cost estimate and a confirm_token instead of running; repeated unchanged by the same user within ten minutes, with approved_credits at or above the estimate or with the confirm_token, it runs once. A resend after that run is refused with no token, except an identical multi-row rows batch, which replays its stored dataset at no charge.

Inputs: tool (required), user_prompt (required), rows, method, +5 more.

hyreflow_workflow_runA
Destructive
Inspect

Queue a run of a saved workflow in this workspace, by name or id. Returns the run id and initial status. A live run charges credits for the tools it calls.

Inputs: workflow (required), user_prompt (required), mode, input.

hyreflow_workflow_runsB
Read-only
Inspect

List recent runs of a workflow with their status and timing. Free.

Inputs: workflow (required), limit.

hyreflow_workflows_listA
Read-only
Inspect

List the cloud workflows saved in this Hyreflow workspace. Free.

Tool Schema Changelog

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

Loading tool schema changelog…

    Related MCP Connectors

    Related MCP Servers

    • F
      license
      Not graded
      quality
      A
      maintenance
      Enables AI assistants to automate recruiter-side candidate sourcing by batch-searching, capturing resume screenshots and share links, scoring and filtering profiles, exporting reports, and sending greetings through a logged-in Chrome session.
      -
    • F
      license
      Not graded
      quality
      A
      maintenance
      Enables AI assistants to automate recruiter workflows by batch-searching candidates, capturing and OCR-ing resume screenshots, scoring and filtering applicants, extracting share links, greeting candidates, and exporting Markdown reports.
      -
    • A
      license
      A
      quality
      B
      maintenance
      Enables clean Markdown scraping, live discovery across six ATS job boards, waterfall decision-maker enrichment, and pre-send validation with approval-gated outreach drafting for B2B and executive prospecting.
      6
      MIT
    Try in Browser

    Glama MCP Gateway

    Add one secure layer between your agents and this server.