com.agentery/agentery

Measured conclusion: Deep-tested. L2 outcome: tools_ok.

Price benchmarks, alternatives & daily price history across 17,000+ AI agents and MCP servers.

Add to your agent

Copy this into your MCP client config:

{
  "mcpServers": {
    "agentery": {
      "url": "https://agentery.com/api/mcp",
      "transport": "streamable-http"
    }
  }
}

Measured tools (23)

• research_capability read-only

  Use for a quick first overview of a buying task in one call: the closest-matching listings (matched on what they do, no fixed categories), the price range and median for comparable products (with n), and a shortlist with observed prices, market_position (below / in line / above market) and handles in compare_ready for compare_providers. Also returns suggested_alternatives. It does not run the comparison. For careful selection prefer search_providers → get_provider_profile → compare_providers. Accepts `task` (aliases: query, q).

  Parameters:

  • task (required) — string — Required — the natural-language capability/task, e.g. 'reconcile supplier invoices' or 'litigation-analysis provider'. Aliases: query, q.
  • sort — string — Shortlist ordering. Default 'match'.
  • limit — number — Shortlist size (1-12, default 5).
  • buyer_tier — string — Optional buyer tier to price against ('team' = Team/SME).
  • cohort_ref — string — Optional (1.17.0): reuse the exact set of comparable providers selected by an earlier price_benchmark / market_report / research_capability call.
  • request_ref — string — Optional task reference (rq_ + 12 hex) from an earlier answer. Continues that task: its remembered facts (quantities, budget, requirements, benchmark selection) apply to this call, and the answer keeps the same request_ref.
  • integrations — array — Optional required integrations, e.g. ["zendesk","slack"] — soft preference; integration status is reported per provider.
  • provider_type — string — Preferred delivery type. 'auto' (default) infers from the task; note 'AI agent' phrasing is treated as generic (neutral), not an agent-only filter. When a type is explicit (mcp/api/agent) matching providers are SOFT-RANKED to the top and the rest are kept as clearly-labelled cross_type_alternative entries — never hard-filtered (no zero-result cliff), and the functional match is never changed. Every provider is labelled with provider_type (public values: agent | mcp | api | unknown) + type_match_score; provider_type{type_rank_boost_applied, boosted_provider_type, result_counts_by_type} is returned.
  • response_mode — string — 'summary' (default) or 'full' (adds tier cohorts, coverage and raw results).
  • max_monthly_usd — number — Optional budget ceiling in USD/month — filters the shortlist and drives suggested_alternatives.

  Hints: read-only yes · destructive no · idempotent not declared · open-world no

• search_providers read-only

  Use when someone wants to find or shortlist AI products, AI agents, MCP servers or APIs for a task, e.g. 'AI tool that transcribes sales calls' or 'MCP server to reply to Zendesk tickets'. Returns ranked candidates with what each does, a fit label (match / partial / weak, naming any mismatch), delivery type, price status (known / free / contact_sales / unknown; unknown is never free) and links. Requirements in the wording are checked per result; unverified ones are marked unknown. Results are candidates to check: open strong ones with get_provider_profile and compare finalists with compare_providers. Thin coverage returns no_match, never padding.

  Parameters:

  • query (required) — string — REQUIRED. Free-text description of the product job you are buying, e.g. 'customer support provider with Zendesk integration' or 'supplier invoice reconciliation'. Not for questions about Agentery itself (upvotes, endpoints): those return status unsupported_request.
  • sort — string — match (default) or price_asc (cheapest observed price first; unpriced providers last)
  • limit — number — Max results (1-50, default 20)
  • billing — array — Only providers with one of these observed billing models, e.g. ["free","freemium","subscription","usage"]
  • filters — object — Optional: industry_fit[], integrations_available[], entity_type[] (agent|tool|infrastructure|service|marketplace|content-community), autonomy_level[] (assistant|workflow automation|agentic|infrastructure), minimum_evidence_quality (low|medium|high)
  • deployment — string — Optional (1.10.0). Keep only providers whose EVIDENCED deployment model matches: hosted = a vendor-published MCP endpoint exists (connect, nothing to install); self_hosted = a published install line (npx/uvx/docker/pip/git clone) and no vendor endpoint; both = both are documented; unknown = no evidence held. 'both' listings satisfy hosted and self_hosted. Evidence comes from the vendor's own pages and source directories (Glama/MCP registry attributes) — never guessed from a repository's existence.
  • request_ref — string — Optional task reference (rq_ + 12 hex) from an earlier answer. Continues that task: its remembered facts (quantities, budget, requirements, benchmark selection) apply to this call, and the answer keeps the same request_ref.
  • provider_type — string — Filter to one provider type — the audited classification dimension (same as the website type chips and AEPI facets); result labels always match this filter. Omit for all types.
  • max_monthly_usd — number — Drop providers whose observed lowest paid tier exceeds this (USD/month). Providers with no observed public price still pass unless require_public_price is true.
  • require_public_price — boolean — Only return providers with an observed public price (default false)

  Hints: read-only yes · destructive no · idempotent not declared · open-world no

• find_market read-only

  Use when someone asks what a kind of product typically costs or who competes in a space, e.g. 'what should I charge for lead-generation automation' or 'tools that monitor competitor pricing'. Maps the task to its market (the nearest providers by meaning, no fixed categories) and returns the market label, provider and priced counts, the nearest providers with observed prices, and pricing_by_tier (median, p25/p75, range and n per buyer tier). When nothing is close it returns no_match or thin_coverage and withholds pricing rather than invent a market. For market plus shortlist in one call use research_capability.

  Parameters:

  • task (required) — string — REQUIRED. A natural-language task, capability or service in plain words, e.g. 'reconcile supplier invoices'. Call as {"task": "…"}; an empty call returns status needs_input with an example and searches nothing.
  • query — string — Alias for task (back-compat only) — prefer task

  Hints: read-only yes · destructive no · idempotent not declared · open-world no

• compare_providers read-only

  Use to compare 2–6 shortlisted listings side by side — plan-level prices (e.g. the Pro tier), capabilities, deployment, licence and how to connect — or to check a quote against alternatives. Inputs resolve to real listings by exact handle, then exact name, never a silent fuzzy swap: unknown inputs come back in unresolved_inputs with suggested_matches and a corrected_call; if only one input is real it is compared with its nearest market peers (comparison_status says so); if none resolve, comparison_status is insufficient_valid_providers. Mixed delivery types are flagged: a hosted agent and an MCP server are not directly equivalent, so compare hosted prices with hosted prices. Over-budget or weak matches get suggested_alternatives. Returns a concise decision view by default (fit, observed plans and prices with source and date, job cost, requirement verdicts, unknowns); pass detail:"full" for every field. Accepts `provider_ids` (aliases: handles, ids, or a comma-separated string).

  Parameters:

  • provider_ids (required) — array — 2-6 provider handles from search_providers/market_gaps, e.g. ["openhands","lexaclaw"]
  • task — string — Optional. The buyer's job in plain words; used as the service_view heading.
  • detail — string — Optional. concise (default): the decision view. full: the complete comparison (all plan lines, evidence checks, deployment, licence, how to connect, requirement evidence excerpts).
  • service — string — Optional. A service recipe whose fixed requirements and evidence fields are applied (see service_view.requirements).
  • optional — array — Optional preferences: reported in service_view but never gating.
  • request_ref — string — Optional task reference (rq_ + 12 hex) from an earlier answer. Continues that task: its remembered facts (quantities, budget, requirements, benchmark selection) apply to this call, and the answer keeps the same request_ref.
  • requirements — array — Optional. Mandatory requirements as plain phrases (e.g. "sanctions screening", "documented MCP interface"). Adds an ADDITIVE service_view: per-provider evidence matrix from stored first-party page text — supported / not_supported / unknown with the excerpt and observation date; unknown never means unsupported.

  Hints: read-only yes · destructive no · idempotent not declared · open-world no

• get_price_index read-only

  Use when asked whether prices of AI agents, tools or MCP servers are rising or falling overall. Returns the current Agent Economy Price Index (AEPI), a like-for-like index of observed agent and MCP pricing (base 100 = 29 Jun 2026; an index level, not a price), with 1-, 7- and 30-day change, plus the same for the four buyer tiers (Individual, Pro, Team/SME, Enterprise). provider_type=agent|mcp gives the standalone index for that delivery type; tier narrows to one tier. For the trend over time use get_price_index_history; for what a particular kind of product costs use get_group_fair_price or price_benchmark.

  Parameters:

  • tier — string — Filter to one buyer tier ('team' = Team/SME). Default 'all'.
  • benchmark_id — string — Optional: a private custom benchmark token (cb_…) from create_custom_benchmark — returns that cohort's current index instead of the economy index. Cannot be combined with niche.
  • provider_type — string — 'all' (default) = the combined whole-economy index; 'agent' or 'mcp' = the standalone index over just that delivery type (own base 100); 'payg' = the standalone pay-as-you-go sub-index (usage rates purchasable without a subscription, engine v2). Agents and MCPs price and move differently, so an MCP buyer should read the 'mcp' index and an agent buyer the 'agent' index.
  • response_mode — string — 'summary' (default) or 'full' (adds exact sub-0.01% moves and repricing counts).

  Hints: read-only yes · destructive no · idempotent not declared · open-world no

• price_benchmark read-only

  Use to judge whether a price is fair or what a capability typically costs, e.g. 'Is $49/month reasonable for an AI SDR for a small team?'. Pass the capability as `query` (aliases: task, niche). Returns observed prices of comparable products — median, p25/p75, range, mean, stdev and n — split by delivery type (agent | mcp) and buyer tier (individual / pro / team_sme / enterprise), never blended across incompatible pricing units. Comparables are the products closest in what they do (no fixed categories). A benchmark describes an observed sample; it is not a quote and not evidence of willingness to pay. Set provider_type and buyer_tier when known. If nothing priced is close it returns resolved:false with a note, never an invented figure.

  Parameters:

  • task — string — Alias of `query` (same text).
  • limit — number — Observations per page in full mode (1–100, default 50).
  • niche — string — Legacy alias of `query`, kept for older clients — prefer `query`.
  • query — string — The capability to benchmark, in natural language, e.g. 'AI code review' or 'supplier invoice reconciliation'. Preferred input.
  • offset — number — Paging offset over the selected observations in full mode.
  • sector — string — Sector name, e.g. 'legal' (ignored if a query is given)
  • currency — string — Currency of proposed_price (ISO code, default USD).
  • buyer_tier — string — Buyer tier being priced. Set when the user describes who is buying (an individual, a professional, a team/SME, or an enterprise). An individual licence must never be represented by the SME or enterprise price.
  • cohort_ref — string — Optional (1.17.0): reuse the exact set of comparable providers selected by an earlier price_benchmark / market_report / research_capability call (its cohort_ref), instead of re-selecting the market from new wording.
  • commitment — string — Billing commitment of proposed_price (default monthly).
  • request_ref — string — Optional task reference (rq_ + 12 hex) from an earlier answer. Continues that task: its remembered facts (quantities, budget, requirements, benchmark selection) apply to this call, and the answer keeps the same request_ref.
  • pricing_unit — string — Billing unit the benchmark is FOR (1.17.0: honoured). Selects the comparable observations; units are never converted into one another, and a thin unit returns its observations and the gap — never a flat-monthly substitute. A query such as 'cost per support ticket' sets it when omitted.
  • provider_type — string — Delivery type being priced. Set when the user says provider, MCP or API. Omit (or 'all') to get the per-type matrix instead of a blended figure. 'api' is recognised but not yet a separate commercial cohort (folded into provider).
  • response_mode — string — 'summary' (default): the selected benchmark with its top observations. 'full': every included observation (paged), with plan, native price, unit, commitment, source and observed date.
  • proposed_price — number — Optional (sellers): a proposed price to position against the selected comparable offers (same unit; currency below). Returns where it sits in the observed range; a percentile only with ≥5 comparable providers. A market reference, not an optimal price.

  Hints: read-only yes · destructive no · idempotent not declared · open-world no

• request_research

  Use when a buying decision hinges on one specific fact about one listing that its profile does not settle, e.g. {"provider_id":"flux_operator","requirement":"Is there a Helm chart for Kubernetes?"} or 'Does the Business plan go to checkout or to contact sales?'. Agentery reads the vendor's own pages, its code repository (read, never run) and the pricing page's buttons, and answers yes / no / partly / unknown with quotes, URLs and observation dates. Usually answered in this response within about 15 s; otherwise call get_research with the job_id after poll_after_seconds. Identical questions share one job. A found statement is the vendor's own claim, not independent verification.

  Parameters:

  • provider_id (required) — string — The listing (provider_id from search_providers).
  • requirement (required) — string — The requirement in plain words, e.g. 'EU data residency', 'integrates with Slack', 'SOC 2 Type II', 'commercial use permitted'.
  • request_ref — string — Optional: the request_ref of the answer that raised the question.

  Hints: read-only no · destructive no · idempotent yes · open-world yes

• get_research read-only

  Status and result of a research job created by request_research. status: queued / running / answered / partly_answered / still_unknown / failed; phase: queued | running | retry_scheduled | completed_answer | completed_unknown | failed. Poll no more often than poll_after_seconds — polling is free and never repeats the work. result: answer (yes/no/partly/unknown), short_answer, evidence per claim (quote, URL, observed date; file path and revision for repositories; element for pricing-page buttons), facts assessed separately (e.g. Dockerfile vs published image vs Helm chart), conflicts and what remains unresolved.

  Parameters:

  • job_id (required) — string — The job_id from request_research (rj_ + 12 hex).

  Hints: read-only yes · destructive no · idempotent not declared · open-world no

• stop_research_updates destructive

  Stop watching a research job (the result stays retrievable with get_research).

  Parameters:

  • job_id (required) — string

  Hints: read-only no · destructive yes · idempotent yes · open-world no

• refine_results destructive

  Use when an earlier search_providers or research_capability answer missed what was meant: pass its request_ref and the correction in plain words (e.g. 'must integrate with Slack', 'budget is $20/month', 'data must stay in the EU'). Agentery re-runs the search with the changed constraints (the others are kept) and returns the new answer plus what changed. source: 'human' (the user's words), 'agent' (your assessment, default) or 'follow_up'. Agentery sees only the request and correction you send, never your wider conversation. Task answers (search_providers, compare_providers, research_capability, price_benchmark, market_report) carry ONE request_ref plus a 'conversation' block: the facts remembered for the task, any optional clarification questions (at most two, one round) and the exact refine_results call to continue. Answer with plain words, 'unknown' or 'skip'; source is one of human, agent, follow_up. Pass the same request_ref to another task tool to continue the task there. References expire 24 h after the last turn.

  Parameters:

  • request_ref (required) — string — The request_ref from the earlier answer (rq_ + 12 hex characters).
  • correction (required) — string — What was missing or wrong, in plain words.
  • source — string — Where the correction came from. Default 'agent'.

  Hints: read-only no · destructive yes · idempotent no · open-world no

• get_group_fair_price read-only

  Use to check what a product of a given kind typically costs: give a task or product type (or a group_id from the group price league) and get its product group's fair price for each buyer tier (individual, pro, team / small business, enterprise) — the median entry monthly price in that tier with its typical range — plus which payment models the group typically uses (free, subscription, usage, one-time, contact sales), usage and one-time medians where at least 3 listings publish them, and the group's price-index change over 90 days. Groups are built from what products do, not from price. Medians of current published prices only; individual listings are not returned — use search_providers for candidates.

  Parameters:

  • query — string — The task or product type, e.g. 'AI meeting notes for sales teams'.
  • group_id — number — Optional: a group id from agentery.com/aepi/groups or from get_provider_profile's product_group.

  Hints: read-only yes · destructive no · idempotent not declared · open-world no

• get_price_index_history read-only

  Use to show how AI agent and MCP prices have moved over time: the dated Agent Economy Price Index series, the same chained like-for-like series agentery.com/aepi charts. Points are index levels (base 100), never prices. Whole-economy series by default; `tier` for one buyer tier; provider_type agent|mcp for one delivery type (own base 100); `period` 30d (default) / 90d / all; response_mode summary (default) or full (adds gap flags). Thin data returns insufficient_history, never an invented series. For what one capability costs use price_benchmark or market_report. Also reads a private custom benchmark's history via benchmark_id.

  Parameters:

  • tier — string — Return one buyer tier's series ('team' = Team/SME). Default 'all' = the headline series.
  • since — string — Optional, for providers that poll: the `cursor` (or `next_cursor`) from your previous call, or an ISO timestamp of your last check. Returns only what changed since then: new_points (newly published days), corrected_points (earlier days whose published level changed, with previous_level) and withdrawn_points, plus next_cursor for the next call. status 'no_changes' when nothing changed. Omit for the full history.
  • period — string — History window. Default '30d'.
  • benchmark_id — string — Optional: a private custom benchmark token (cb_…) — returns that cohort's dated series instead of the economy series. Cannot be combined with niche.
  • provider_type — string — 'all' (default) = the combined whole-economy series, or the standalone 'agent' / 'mcp' / 'subscription' / 'hybrid' / 'one_off' / 'payg' = the billing-LENS series (they cut across provider/mcp; a rate sits in one delivery type AND one lens; own base 100) — 'payg' (pay-as-you-go, engine v2) series (own base 100).
  • response_mode — string — 'summary' (default, compact) or 'full'.

  Hints: read-only yes · destructive no · idempotent not declared · open-world no

• market_gaps read-only

  Use when a seller or investor asks which tasks people look for that few paid products serve. Clusters requests seen on this MCP server by meaning and returns those far from any paid provider: the request phrasing, distinct_callers, raw_requests, the nearest paid provider and its similarity (low = under-served). headline = jobs asked by two or more callers; weak_leads = one caller; information_requests = questions about a named product. These are research leads from limited traffic, not buyer counts or proof of a market-wide gap; few or none is normal while volume is low. Marked test traffic is excluded. No arguments needed.

  Parameters:

  • rank — string — gaps (default): whitespace with money, crowded excluded. hot: most active by market pulse, crowding ignored.
  • limit — number — Max gaps (1-50, default 15)
  • sector — string — Optional sector filter, e.g. 'legal', 'healthcare'
  • include_own — boolean — Also list leads asked ONLY by you (default false: one caller's repeated searches are not independent demand; they are counted in your_own_only_excluded)

  Hints: read-only yes · destructive no · idempotent not declared · open-world no

• suggest_alternatives read-only

  Find related alternatives to a known provider, ranked by text-embedding nearness to that provider's OWN profile (NO category lookup), each with observed price, endpoint liveness, community upvotes and how_to_connect (website, docs, mcp endpoint). For cheaper_only, inspect whether the reference price and candidate prices support a valid comparison: an empty response may reflect a missing or incompatible reference price rather than the absence of alternatives (the response says which). Accepts `agent_id` (aliases: handle, id). These substitutes are also surfaced inside research_capability and compare_providers. Each alternative also carries `deployment` (evidenced model) and how_to_connect.install / repository (1.10.0).

  Parameters:

  • agent_id (required) — string — Handle of the provider to find substitutes for, e.g. 'openhands'
  • limit — number — Max alternatives (1-10, default 5)
  • cheaper_only — boolean — Only keep alternatives priced below the subject's lowest monthly price. Free/freemium providers always qualify; providers with no observed price are excluded. Default false.

  Hints: read-only yes · destructive no · idempotent not declared · open-world no

• demand_signals read-only

  Inspect searches by external callers in the last 90 days that found no provider or only weak matches (best relevance below 0.62), shown as generalised job labels and ranked by distinct callers. Most entries come from a single caller: treat those as leads. These are limited coverage signals from Agentery's own callers — not proof that a product does not exist, and not proof that a market has paying demand. Not a prerequisite for choosing a product. Empty args ({}) return the current list; an empty response means there is insufficient qualifying evidence (status insufficient_evidence + next_step) — it is never filled from search popularity, page views or trending queries.

  Parameters:

  • limit — number — Max signals (1-50, default 20)
  • include_own — boolean — Also list signals that come ONLY from your own searches (default false; counted in your_own_only_excluded)

  Hints: read-only yes · destructive no · idempotent not declared · open-world no

• report_outcome

  Report the result of ACTUALLY USING a listed provider for a task. Testing Agentery's connection or retrieval does not establish that the listed provider worked — do not report those. Reports are self-reported evidence subject to eligibility checks: they are correlated with your recent retrievals, improve ranking accuracy, and unlock higher rate limits for contributors. Only reports we can match to one of YOUR retrievals (search_providers / get_provider_profile / compare_providers / suggest_alternatives naming that provider, last 48h) carry weight; unmatched reports are stored but unweighted. Aggregates surface as `reported_success` on profile/comparison cards once 5+ distinct reporters exist (90-day window). Callers with 5+ correlated reports in 30 days get a doubled per-minute rate limit. Send an x-agentery-key header to keep one reporter identity across IPs (it is stored only as a hash).

  Parameters:

  • agent_id (required) — string — Handle of the provider you used, as returned by search_providers/get_provider_profile/compare_providers
  • outcome (required) — string — Did the provider accomplish the task you hired it for?
  • note — string — Optional free-text detail (capped at 300 chars)
  • task_type — string — Optional short task label, e.g. 'code-review', 'lead-enrichment'
  • latency_ms — number — Optional end-to-end latency of the provider in milliseconds
  • error_class — string — Optional failure class, e.g. 'timeout', 'auth', 'wrong-output', 'endpoint-down'

  Hints: read-only no · destructive no · idempotent not declared · open-world no

• get_provider_profile read-only

  Use to check one specific listing before recommending or connecting it: plans and prices with billing units, what it does, integrations, deployment (hosted / self_hosted / both / unknown, with evidence), licence (named licence only), liveness and how to connect (website, docs, MCP endpoint with a copy-paste config_snippet, A2A agent card, API, install). Fields are null when the vendor publishes nothing; nothing is guessed. price_applies_to flags a stored price that belongs to the vendor's platform rather than this connector. product_group names the listing's product group with its fair price per buyer tier and 90-day price-index change. reported_success stays null until 5+ distinct reporters in 90 days; after actually using a listing, call report_outcome.

  Parameters:

  • provider_id (required) — string — The provider_id/handle returned by search_providers or compare_providers

  Hints: read-only yes · destructive no · idempotent not declared · open-world no

• get_provider read-only

  For buying decisions prefer get_provider_profile (prices, deployment, evidence); use this only for the short public directory card of one provider by handle or registration number: bio, source URLs, X-verification status, entity type, community rating and structured profile when available.

  Parameters:

  • handle — string — Provider handle, e.g. 'openhands'
  • regNum — number — Registration number, e.g. 2432

  Hints: read-only yes · destructive no · idempotent not declared · open-world no

• market_report read-only

  Deep-dive ONE market before building or investing — the market is the semantic neighbourhood of your natural-language query (nearest providers by text embedding, NO fixed category). Every field is MEASURED: the observed-pricing benchmark separated by provider type and buyer tier (median, mean, stdev, p25/p75, min–max range and n via the canonical pricing engine), how many providers are in the neighbourhood and how many are priced, and the top providers already competing there with their observed price and relevance. Pass `query` (a natural-language capability or market, e.g. 'customer support chatbot'). For market + pricing + a ready shortlist in one call, use research_capability.

  Parameters:

  • query (required) — string — Natural-language capability or market, e.g. 'customer support chatbot' or 'ai phishing detection'.
  • limit — number — full mode: members per page (1–150, default 50).
  • offset — number — full mode: paging offset over members (default 0).
  • cohort_ref — string — Optional (1.17.0): reuse the exact set of comparable providers selected by an earlier price_benchmark / market_report / research_capability call (its cohort_ref), instead of re-selecting the market from new wording.
  • request_ref — string — Optional task reference (rq_ + 12 hex) from an earlier answer. Continues that task: its remembered facts (quantities, budget, requirements, benchmark selection) apply to this call, and the answer keeps the same request_ref.
  • response_mode — string — 'summary' (DEFAULT): neighbourhood counts, per-type/per-tier price cohorts and the top 12 providers. 'full' (1.17.0): EVERY member of the neighbourhood, paged with offset / limit, each with its price reading (plan, unit, currency, source, observed date).

  Hints: read-only yes · destructive no · idempotent not declared · open-world no

• create_custom_benchmark

  Use when someone wants to keep watching the prices of products they choose (e.g. five named writing tools). Creates a PRIVATE custom benchmark (a saved, calculated peer cohort) over Agentery's data — no account needed. Two modes: (A) explicit members: pass `members` (a list of exact handles; product names/domains resolve where unambiguous). (B) fork a market: pass `base_niche` (its slug) plus optional `remove`/`add`. Returns a one-time secret `benchmark_id` (cb_… token) — store it; it's your only key. Use it later in get/update/delete and in market_report/get_price_index/get_price_index_history. Ambiguous names are returned as candidates, never silently resolved; unresolved inputs block creation unless allow_partial:true. All prices/history are computed from Agentery's immutable observations; canonical market data is never changed.

  Parameters:

  • add — array — members to add
  • name — string — Optional private label
  • remove — array — Mode B: members to drop from the forked market
  • members — array — Mode A: exact handles (preferred), product names or domains
  • base_niche — string — Mode B: slug of the canonical market to fork
  • allow_partial — boolean — Create with only the resolved members when some inputs don't resolve (default false)

  Hints: read-only no · destructive no · idempotent no · open-world no

• get_custom_benchmark read-only

  Get a private custom benchmark's current report: members, current stats (headline median/quartiles only when ≥3 comparable priced members — monthly, per-seat and per-call prices are never blended), buyer-tier / provider-type / pricing-unit cohorts, historical index, and data coverage. Pass `benchmark_id` (your cb_ token) as an ARGUMENT.

  Parameters:

  • benchmark_id (required) — string — Your cb_ token (bearer secret; passed as an argument, never a URL)
  • as_of — string — Optional YYYY-MM-DD — reproduce the exact stats + index as they were on that date, using this version's fixed membership
  • version — number — Optional benchmark version (default latest)
  • response_mode — string — full includes the index series

  Hints: read-only yes · destructive no · idempotent not declared · open-world no

• update_custom_benchmark destructive

  Add/remove members or rename a custom benchmark. Creates a NEW immutable version (the previous version stays fully reproducible) and returns the exact change-impact on the median/quartiles/index. Pass `benchmark_id`.

  Parameters:

  • benchmark_id (required) — string — Your cb_ token
  • add — array
  • remove — array
  • rename — string

  Hints: read-only no · destructive yes · idempotent no · open-world no

• delete_custom_benchmark destructive

  Disable access to a custom benchmark. Keeps only a minimal audit record; no underlying Agentery data is touched. Pass `benchmark_id`.

  Parameters:

  • benchmark_id (required) — string — Your cb_ token

  Hints: read-only no · destructive yes · idempotent yes · open-world no

Publisher website

Measured by MCPYP probing. Untested fields are omitted, never estimated. Listing is always free; MCPYP never proxies calls or stores user tokens.