// MCP TOKEN COST

The 100Hires - AI ATS & Recruitment Software MCP server costs 14,393 tokens before the first call.

Every request your agent makes carries every tool definition this server exposes — context your code, documents and conversation can't use, mostly for tools the agent never calls. You don't need them all in the window, and you don't have to pay for them.

QUICK ANSWER The 100Hires - AI ATS & Recruitment Software MCP server's 136 tool definitions consume 14,393 tokens — 7.2% of a 200k context window, and 7.7× the median MCP server (1,862 tokens). A scoped grant exposing only the tools you use cuts that roughly in proportion.

MEASURED FROM SCHEMAS tiktoken o200k_base · rank #1226 of 12,722 measured servers · refreshed every build Method →

// CONTEXT WINDOW SHARE

What that costs 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 7.2%

1M WINDOW 1.4%

Corpus context: 100Hires - AI ATS & Recruitment Software ranks #1226 of 12,722 measured MCP servers by definition cost. The median is 1,862 tokens, p90 is 13,674, and the heaviest (Ainumbers Mcp Apps) is 442,047 — 221% of a 200k window on its own. New to this? See MCP token cost and context window in the glossary.

Token cost is one axis. See the risk picture across your whole stack →

// PER-TOOL BREAKDOWN

Where the 14,393 tokens go.

Each row is one tool definition as a tools/list entry — name, description and input schema — counted with o200k_base. Average: 106 tokens per tool.

Tool	Category	Tokens	% of server
hires_update_job	Write	714	5.0%
hires_create_job	Write	708	4.9%
hires_create_nurture_campaign	Write	697	4.8%
hires_update_nurture_campaign	Write	690	4.8%
hires_batch_create_messages	Write	274	1.9%
hires_list_applications	Read	262	1.8%
hires_upload_attachment	Write	260	1.8%
hires_create_candidate	Write	251	1.7%
hires_update_candidate	Write	250	1.7%
hires_list_candidates	Read	236	1.6%
hires_send_candidate_message	Write	233	1.6%
hires_list_candidate_activities	Read	228	1.6%
hires_submit_career_application	Write	223	1.5%
hires_list_jobs	Read	218	1.5%
hires_update_message	Write	213	1.5%
hires_patch_message	Write	202	1.4%
hires_create_company	Write	187	1.3%
hires_update_company	Write	186	1.3%
hires_list_interviews	Read	185	1.3%
hires_list_messages	Read	176	1.2%
hires_update_application	Write	176	1.2%
hires_create_note	Write	170	1.2%
hires_create_application	Write	168	1.2%
hires_upload_candidate_file	Write	145	1.0%
hires_create_interview	Write	142	1.0%
hires_submit_feedback	Write	139	1.0%
hires_list_template_placeholders	Read	127	0.9%
hires_list_candidate_messages	Read	123	0.9%
hires_prepare_template_placeholders	Read	115	0.8%
hires_update_career_site_settings	Write	115	0.8%
hires_upload_application_attachment	Write	115	0.8%
hires_list_notes	Read	113	0.8%
hires_list_career_jobs	Read	111	0.8%
hires_transfer_application	Financial	106	0.7%
hires_create_email_template	Write	105	0.7%
hires_reject_application	Write	103	0.7%
hires_update_notification_message	Write	103	0.7%
hires_download_attachment	Read	101	0.7%
hires_create_job_webhook	Write	101	0.7%
hires_set_job_status	Write	100	0.7%
hires_create_question	Write	95	0.7%
hires_create_webhook	Write	95	0.7%
hires_update_question	Write	93	0.6%
hires_update_note	Write	92	0.6%
hires_list_application_evaluations	Read	91	0.6%
hires_batch_reject_applications	Write	90	0.6%
hires_disqualify_candidate	Read	88	0.6%
hires_get_candidate_resume	Read	86	0.6%
hires_advance_application	Read	82	0.6%
hires_move_application	Write	80	0.6%
hires_batch_remove_from_boards	Destructive	79	0.5%
hires_list_application_stage_history	Read	79	0.5%
hires_rotate_webhook_secret	Read	79	0.5%
hires_batch_publish_to_boards	Write	79	0.5%
hires_update_form_question	Write	79	0.5%
hires_rotate_job_webhook_secret	Read	78	0.5%
hires_batch_move_applications	Write	78	0.5%
hires_update_email_template	Write	77	0.5%
hires_remove_from_job_board	Destructive	76	0.5%
hires_list_email_templates	Read	76	0.5%
hires_list_workflow_stages	Read	76	0.5%
hires_publish_to_job_board	Write	76	0.5%
hires_list_forms	Read	75	0.5%
hires_batch_remove_tags	Destructive	74	0.5%
hires_batch_add_tags	Write	74	0.5%
hires_get_career_site_settings	Read	73	0.5%
hires_create_form	Write	70	0.5%
hires_update_form	Write	70	0.5%
hires_get_job	Read	69	0.5%
hires_list_user_mail_accounts	Read	69	0.5%
hires_get_career_job	Read	66	0.5%
hires_list_candidate_interviews	Read	66	0.5%
hires_unreject_application	Read	66	0.5%
hires_add_hiring_team_member	Write	66	0.5%
hires_cancel_all_notification_messages	Destructive	65	0.5%
hires_hire_application	Write	65	0.5%
hires_list_company_id_mail_accounts	Read	64	0.4%
hires_add_candidate_tags	Write	64	0.4%
hires_get_notification_message	Read	63	0.4%
hires_list_candidate_files	Read	63	0.4%
hires_delete_job_webhook	Destructive	61	0.4%
hires_get_application	Read	61	0.4%
hires_remove_candidate_tag	Destructive	58	0.4%
hires_delete_webhook	Destructive	57	0.4%
hires_get_ai_score	Read	57	0.4%
hires_get_note	Read	57	0.4%
hires_list_job_boards	Read	56	0.4%
hires_batch_job_boards	Read	55	0.4%
hires_get_interview	Read	55	0.4%
hires_list_company_mail_accounts	Read	55	0.4%
hires_get_workflow_stages	Read	54	0.4%
hires_list_job_webhooks	Read	53	0.4%
hires_get_user	Read	52	0.4%
hires_list_hiring_team	Read	52	0.4%
hires_list_nurture_campaigns	Read	52	0.4%
hires_delete_email_template	Destructive	50	0.3%
hires_list_questions	Read	50	0.3%
hires_list_languages	Read	49	0.3%
hires_delete_candidate	Destructive	48	0.3%
hires_get_candidate	Read	48	0.3%
hires_list_candidate_tags	Read	48	0.3%
hires_list_users	Read	48	0.3%
hires_get_evaluation	Read	47	0.3%
hires_restore_company	Write	46	0.3%
hires_delete_job	Destructive	45	0.3%
hires_get_message	Read	45	0.3%
hires_get_nurture_campaign	Read	45	0.3%
hires_delete_notification_message	Destructive	44	0.3%
hires_delete_nurture_campaign	Destructive	44	0.3%
hires_list_application_attachments	Read	44	0.3%
hires_list_webhooks	Read	44	0.3%
hires_delete_company	Destructive	43	0.3%
hires_list_companies	Read	43	0.3%
hires_get_email_template	Read	42	0.3%
hires_get_form	Read	41	0.3%
hires_delete_message	Destructive	40	0.3%
hires_get_question	Read	40	0.3%
hires_list_statuses	Read	40	0.3%
hires_delete_question	Destructive	39	0.3%
hires_get_company	Read	39	0.3%
hires_list_employment_types	Read	39	0.3%
hires_delete_application	Destructive	38	0.3%
hires_list_rejection_reasons	Read	38	0.3%
hires_list_workflows	Read	37	0.3%
hires_delete_form	Destructive	36	0.3%
hires_delete_note	Destructive	35	0.2%
hires_list_departments	Read	34	0.2%
hires_list_sources	Read	34	0.2%
hires_list_tags	Read	34	0.2%
hires_get_billing	Read	33	0.2%
hires_list_boards	Read	30	0.2%
hires_list_education_levels	Read	29	0.2%
hires_list_experience_levels	Read	29	0.2%
hires_list_origins	Read	28	0.2%
hires_list_question_types	Read	28	0.2%
hires_list_categories	Read	27	0.2%

// CUT THE COST

Your agent uses a handful of these tools. It pays for all 136.

You don't need all 136 of those definitions in the window. PolicyLayer is an MCP gateway that sits in front of 100Hires - AI ATS & Recruitment Software: only the tools you grant are exposed to the agent, the rest never load. A smaller window means a sharper agent — less noise when it picks a tool — and every request costs less:

Grant scope	Definition cost	Reduction
All 136 tools (no gateway)	14,393 tokens	—
3 granted tools	~317 tokens	−98%
5 granted tools	~529 tokens	−96%
10 granted tools	~1,058 tokens	−93%

The risk dividend: 19 of these 136 tools are critical-risk (destructive or financial) and cost 1,038 tokens (7% of the definition load). Block them — the recommended starter policy — and you reclaim that context before tuning anything else.

Create a free account and register 100Hires - AI ATS & Recruitment Software — nothing to install.
Grant only the tools you use — ungranted definitions never enter the context window.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

CUT 100HIRES - AI ATS & RECRUITMENT SOFTWARE TOKEN COST →

Instant setup, no code required.

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 136 tool definitions total 14,393 tokens — 7.2% 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 317 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 20-10-2026 from the PolicyLayer scan database over all 136 catalogued 100Hires - AI ATS & Recruitment Software tools. Counts refresh with every site build.