// MCP TOKEN COST

The 100Hires - AI ATS & Recruitment Software MCP server costs 23,329 tokens before the first call.

Connect 100Hires - AI ATS & Recruitment Software and its 131 tool definitions are loaded into the model's context on every request — 12% of a 200k window spent before your agent does anything.

QUICK ANSWER The 100Hires - AI ATS & Recruitment Software MCP server's tool definitions consume 23,329 tokens — 12× the median MCP server (1,905 tokens). A scoped grant exposing only the tools you use cuts that roughly in proportion.

MEASURED FROM SCHEMAS 131 tools · 23,329 tokens · 12% of 200k · 2.3% of 1M Method →

// CONTEXT WINDOW SHARE

What that buys before your agent starts working.

Tool definitions are overhead: they occupy context on every request and compete with your code, documents and conversation history for the same window.

200K WINDOW 12%

1M WINDOW 2.3%

Corpus context: 100Hires - AI ATS & Recruitment Software ranks #46 of 3,213 measured MCP servers by definition cost. The median is 1,905 tokens, p90 is 7,952, and the heaviest (Fusionauth) is 183,337 — 92% of a 200k window on its own.

// PER-TOOL BREAKDOWN

Where the 23,329 tokens go.

Each row is one tool definition as a tools/list entry — name, description and input schema — counted with o200k_base. Average: 178 tokens per tool.

Tool	Category	Tokens	% of server
hires_create_nurture_campaign	Write	1,433	6.1%
hires_update_nurture_campaign	Write	1,406	6.0%
hires_create_job	Write	931	4.0%
hires_update_job	Write	881	3.8%
hires_list_applications	Read	527	2.3%
hires_list_candidates	Read	471	2.0%
hires_list_jobs	Read	454	1.9%
hires_batch_create_messages	Write	412	1.8%
hires_upload_attachment	Write	412	1.8%
hires_list_interviews	Read	382	1.6%
hires_list_messages	Read	372	1.6%
hires_create_candidate	Write	366	1.6%
hires_list_candidate_activities	Read	358	1.5%
hires_submit_career_application	Write	344	1.5%
hires_send_candidate_message	Write	326	1.4%
hires_update_candidate	Write	294	1.3%
hires_update_message	Write	294	1.3%
hires_patch_message	Write	285	1.2%
hires_create_note	Write	276	1.2%
hires_update_company	Write	273	1.2%
hires_create_company	Write	269	1.2%
hires_create_application	Write	259	1.1%
hires_upload_candidate_file	Write	259	1.1%
hires_update_application	Write	246	1.1%
hires_list_notes	Read	240	1.0%
hires_list_candidate_messages	Read	234	1.0%
hires_list_template_placeholders	Read	220	0.9%
hires_create_interview	Write	217	0.9%
hires_download_attachment	Read	214	0.9%
hires_list_email_templates	Read	212	0.9%
hires_list_career_jobs	Read	207	0.9%
hires_submit_feedback	Write	199	0.9%
hires_list_forms	Read	190	0.8%
hires_create_email_template	Write	188	0.8%
hires_upload_application_attachment	Write	184	0.8%
hires_advance_application	Read	173	0.7%
hires_update_notification_message	Write	165	0.7%
hires_prepare_template_placeholders	Read	162	0.7%
hires_reject_application	Write	161	0.7%
hires_transfer_application	Financial	159	0.7%
hires_get_candidate_resume	Read	155	0.7%
hires_list_application_evaluations	Read	154	0.7%
hires_list_candidate_files	Read	153	0.7%
hires_update_note	Write	145	0.6%
hires_create_question	Write	144	0.6%
hires_set_job_status	Write	140	0.6%
hires_list_application_stage_history	Read	139	0.6%
hires_update_email_template	Write	134	0.6%
hires_update_question	Write	132	0.6%
hires_list_workflow_stages	Read	130	0.6%
hires_move_application	Write	130	0.6%
hires_update_form_question	Write	126	0.5%
hires_disqualify_candidate	Read	125	0.5%
hires_create_job_webhook	Write	123	0.5%
hires_publish_to_job_board	Write	123	0.5%
hires_batch_remove_from_boards	Destructive	122	0.5%
hires_list_user_mail_accounts	Read	122	0.5%
hires_batch_publish_to_boards	Write	121	0.5%
hires_list_candidate_interviews	Read	120	0.5%
hires_batch_reject_applications	Write	120	0.5%
hires_batch_remove_tags	Destructive	119	0.5%
hires_batch_move_applications	Write	119	0.5%
hires_remove_from_job_board	Destructive	118	0.5%
hires_list_company_id_mail_accounts	Read	118	0.5%
hires_get_job	Read	117	0.5%
hires_batch_add_tags	Write	117	0.5%
hires_get_career_job	Read	115	0.5%
hires_add_candidate_tags	Write	115	0.5%
hires_list_nurture_campaigns	Read	114	0.5%
hires_list_users	Read	113	0.5%
hires_hire_application	Write	112	0.5%
hires_create_form	Write	110	0.5%
hires_add_hiring_team_member	Write	109	0.5%
hires_create_webhook	Write	109	0.5%
hires_get_note	Read	107	0.5%
hires_delete_job_webhook	Destructive	104	0.4%
hires_get_interview	Read	104	0.4%
hires_update_form	Write	104	0.4%
hires_list_questions	Read	103	0.4%
hires_get_workflow_stages	Read	102	0.4%
hires_unreject_application	Read	101	0.4%
hires_cancel_all_notification_messages	Destructive	100	0.4%
hires_list_company_mail_accounts	Read	100	0.4%
hires_get_application	Read	99	0.4%
hires_get_notification_message	Read	98	0.4%
hires_get_user	Read	96	0.4%
hires_remove_candidate_tag	Destructive	94	0.4%
hires_get_ai_score	Read	94	0.4%
hires_get_evaluation	Read	94	0.4%
hires_list_job_boards	Read	94	0.4%
hires_delete_webhook	Destructive	93	0.4%
hires_list_companies	Read	90	0.4%
hires_batch_job_boards	Read	88	0.4%
hires_list_candidate_tags	Read	85	0.4%
hires_list_hiring_team	Read	85	0.4%
hires_list_application_attachments	Read	83	0.4%
hires_list_job_webhooks	Read	83	0.4%
hires_get_candidate	Read	80	0.3%
hires_get_message	Read	80	0.3%
hires_list_tags	Read	80	0.3%
hires_list_workflows	Read	80	0.3%
hires_delete_job	Destructive	79	0.3%
hires_list_rejection_reasons	Read	79	0.3%
hires_delete_candidate	Destructive	78	0.3%
hires_delete_email_template	Destructive	78	0.3%
hires_delete_nurture_campaign	Destructive	78	0.3%
hires_delete_notification_message	Destructive	77	0.3%
hires_get_nurture_campaign	Read	76	0.3%
hires_list_departments	Read	76	0.3%
hires_restore_company	Write	76	0.3%
hires_get_email_template	Read	75	0.3%
hires_list_sources	Read	75	0.3%
hires_delete_application	Destructive	74	0.3%
hires_delete_question	Destructive	73	0.3%
hires_get_company	Read	71	0.3%
hires_delete_message	Destructive	70	0.3%
hires_delete_company	Destructive	69	0.3%
hires_delete_note	Destructive	69	0.3%
hires_get_form	Read	67	0.3%
hires_get_question	Read	67	0.3%
hires_list_webhooks	Read	65	0.3%
hires_delete_form	Destructive	62	0.3%
hires_list_statuses	Read	46	0.2%
hires_list_employment_types	Read	45	0.2%
hires_get_billing	Read	42	0.2%
hires_list_question_types	Read	39	0.2%
hires_list_boards	Read	38	0.2%
hires_list_education_levels	Read	38	0.2%
hires_list_origins	Read	37	0.2%
hires_list_categories	Read	36	0.2%
hires_list_experience_levels	Read	35	0.2%

// SCOPED GRANT

Most agents use a handful of these tools. They pay for all 131.

A PolicyLayer grant exposes only the tools you allow — ungranted definitions are filtered out of the tool list, so they never enter the context window. Estimates below assume typical-weight tools (178 tokens each).

Grant scope	Definition cost	Reduction
All 131 tools (no gateway)	23,329 tokens	—
3 granted tools	~534 tokens	−98%
5 granted tools	~890 tokens	−96%
10 granted tools	~1,781 tokens	−92%

Model your own stack in the token-cost calculator, or see the 100Hires - AI ATS & Recruitment Software policy for what a sensible grant looks like.

//FAQ

100Hires - AI ATS & Recruitment Software token-cost questions.

How many tokens does the 100Hires - AI ATS & Recruitment Software MCP server use?+

Its 131 tool definitions total 23,329 tokens — 12% of a 200k context window — measured with tiktoken o200k_base over the serialised tools/list payload. Exact counts vary slightly by client and model.

Why does 100Hires - AI ATS & Recruitment Software consume tokens before I send a message?+

MCP clients load every connected server's tool definitions — name, description, and input schema — into the model's context so it knows what it can call. That payload is charged against your context window on every request, whether or not a tool is used.

How do I reduce 100Hires - AI ATS & Recruitment Software's token usage?+

Expose fewer tools. A PolicyLayer grant scopes 100Hires - AI ATS & Recruitment Software to only the tools you allow — ungranted definitions are filtered out of the tool list, so they never enter the context window. A grant of 3 typical tools costs roughly 534 tokens, a 98% reduction.

Does deferred tool loading fix this?+

Partially, in some clients. Claude Code defers MCP tool schemas behind a tool-search step by default, and VS Code has experimental grouping — but you still pay tokens per search and reload, and Cursor, Windsurf and Gemini CLI load definitions upfront. Reducing the exposed tool set cuts the cost in every client.

// METHOD & REVIEW

How these numbers were measured.

01

Serialisation

Each tool is serialised as a tools/list entry — name, description, input schema — from the schemas in the PolicyLayer scan database. Clients differ slightly in framing, so treat counts as close estimates.

02

Tokeniser

tiktoken o200k_base (GPT-4o/o-series). Anthropic's current tokeniser isn't published, so Claude's exact counts will differ; for English text and JSON schemas the totals are close enough to treat these as estimates.

03

Deferred loading

Some clients now defer schema loading (Claude Code's tool search; VS Code experimental grouping). You still pay per search and reload — and Cursor, Windsurf and Gemini CLI load everything upfront.

Computed 07-06-2026 from the PolicyLayer scan database over all 131 catalogued 100Hires - AI ATS & Recruitment Software tools. Counts refresh with every site build.