Agentery MCP server
com.agentery/agenteryagentery.comstreamable-httpv1.28.2Scanned
Find and compare 41,000+ AI agents, MCP servers and APIs, with daily prices and the AEPI price index
23 tools: 4 can delete or cancel things, 6 change things and 13 only read.
- Reads private data · 3
- Reads text others write · 3
- Can send data out · 0
- No findings
Tools listed without sign-in. Remote posture
With Anlyon
4 tools here can delete or cancel things. Govern them.
- Anlyon lists the tools and adopts none.
- Each tool you adopt gets approvals and receipts.
- Your agent never holds the key.
A tool your agent calls directly is not routed through Anlyon and is not governed by it. Anlyon Radar only lists and labels, and these labels are the same either way.
What the Agentery MCP server can do
The Agentery MCP server is published by agentery.com, a domain the MCP Registry verified. It has 23 tools. It can delete or cancel things (4 tools: stop_research_updates, refine_results, update_custom_benchmark and delete_custom_benchmark) and create or change data (6 tools: research_capability, price_benchmark, request_research, report_outcome and 2 more). 13 tools only read.
3 tools read private data (suggest_alternatives, get_provider_profile and get_provider); 3 tools bring in text other people can write (request_research, suggest_alternatives and get_provider_profile).
None of the fixed checks matched anything in its tool definitions. That is not a safety guarantee.
Its remote endpoint lists its tools without sign-in, and its tools changed 3 times since Anlyon Radar first saw them.
Last scanned Nov 15, 2026, version 1.28.2.
Tools
Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.
23 tools
Deletes or cancels 4Claude Code: deny
delete_custom_benchmarkDisable access to a custom benchmark.No findings
Why it is in this group
- The name "delete_custom_benchmark" says "delete": a word for removing or ending something.
- The server marks it destructive (destructiveHint: true).
Description, as the server wrote it Disable access to a custom benchmark. Keeps only a minimal audit record; no underlying Agentery data is touched. Pass `benchmark_id`.
Annotations the server declares
- title: Delete custom benchmark
- readOnlyHint: false
- destructiveHint: true
- idempotentHint: true
- openWorldHint: false
refine_resultsUse 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.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it destructive (destructiveHint: true).
Description, as the server wrote it 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.
Annotations the server declares
- title: Refine search results
- readOnlyHint: false
- destructiveHint: true
- idempotentHint: false
- openWorldHint: false
stop_research_updatesStop watching a research job (the result stays retrievable with get_research).No findings
Why it is in this group
- The name "stop_research_updates" says "stop": a word for a change.
- The server marks it destructive (destructiveHint: true).
Description, as the server wrote it Stop watching a research job (the result stays retrievable with get_research).
Annotations the server declares
- title: Stop research updates
- readOnlyHint: false
- destructiveHint: true
- idempotentHint: true
- openWorldHint: false
update_custom_benchmarkAdd/remove members or rename a custom benchmark.No findings
Why it is in this group
- The name "update_custom_benchmark" says "update": a word for a change.
- The server marks it destructive (destructiveHint: true).
Description, as the server wrote it 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`.
Annotations the server declares
- title: Update custom benchmark
- readOnlyHint: false
- destructiveHint: true
- idempotentHint: false
- openWorldHint: false
Changes things 6Claude Code: ask
create_custom_benchmarkUse when someone wants to keep watching the prices of products they choose (e.g.No findings
Why it is in this group
- The name "create_custom_benchmark" says "create": a word for a change.
Description, as the server wrote it 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.
Annotations the server declares
- title: Create custom benchmark
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: false
market_reportMeasures ONE market in depth before building or investing: the full observed price distribution by provider type and buyer tier, and the providers competing there.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it Measures ONE market in depth before building or investing: the full observed price distribution by provider type and buyer tier, and the providers competing there. Use this when you need detailed market numbers, not a quick map. The market is the semantic neighbourhood of your query (nearest providers by text embedding, NO fixed category). Every field is MEASURED: the observed-pricing benchmark (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 competing providers with observed price and relevance. Pass `query` (e.g. 'customer support chatbot'). Use find_market instead for a quick market map; research_capability for market + pricing + a ready shortlist in one call; search_providers to pick a product.
Annotations the server declares
- title: Get market report
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
price_benchmarkJudges a specific price or quote against the closest comparable products by what they do (no fixed categories), in the buyer's tier and pricing unit.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it Judges a specific price or quote against the closest comparable products by what they do (no fixed categories), in the buyer's tier and pricing unit. Use this when asked 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. 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. Use get_group_fair_price instead for a broad group-wide guide; find_market for who competes.
Annotations the server declares
- title: Benchmark a price
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
report_outcomeReport the result of ACTUALLY USING a listed provider for a task.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
Description, as the server wrote it 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).
Annotations the server declares
- title: Report provider outcome
- readOnlyHint: false
- destructiveHint: false
- openWorldHint: false
request_researchUse when a buying decision hinges on one specific fact about one listing that its profile does not settle, e.g.Reads text others writeNo findings
Why it is in this group
- The name "request_research" says "request": a word for a change.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it 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.
Annotations the server declares
- title: Request product research
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
research_capabilityGives a one-call first overview of a buying task: market prices, a short priced shortlist and alternatives together.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it Gives a one-call first overview of a buying task: market prices, a short priced shortlist and alternatives together. Use this when you want a quick picture: the closest listings (matched on what they do, no fixed categories), 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, plus suggested_alternatives. It does not run the comparison. Use search_providers → get_provider_profile → compare_providers instead for careful selection; price_benchmark to judge one price. Accepts `task` (aliases: query, q).
Annotations the server declares
- title: Research a capability
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
Only reads 13Show 13 read-only tools
compare_providersUse to compare 2–6 shortlisted listings side by side — plan-level prices (e.g.No findings
Why it is in this group
- The name "compare_providers" says "compare": a word for reading.
Description, as the server wrote it 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).
Annotations the server declares
- title: Compare providers
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
demand_signalsLists searches that found nothing good: queries by external callers in the last 90 days that returned no provider or only weak matches (best relevance below 0.62).No findings
Why it is in this group
- The description's first verb is "list": a word for reading.
Description, as the server wrote it Lists searches that found nothing good: queries by external callers in the last 90 days that returned no provider or only weak matches (best relevance below 0.62). Use this when you want searches Agentery could not answer well, as generalised job labels 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 insufficient qualifying evidence (status insufficient_evidence + next_step) — it is never filled from search popularity, page views or trending queries. Use market_gaps instead for jobs that few paid products serve.
Annotations the server declares
- title: View demand signals
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
find_marketMaps a task to its market: who competes there, how many are priced, and the price level per buyer tier.No findings
Why it is in this group
- The name "find_market" says "find": a word for reading.
Description, as the server wrote it Maps a task to its market: who competes there, how many are priced, and the price level per buyer tier. Use this when someone asks who competes in a space or what a kind of product costs, e.g. 'tools that monitor competitor pricing'. Returns the market label (nearest providers by meaning, no fixed categories), 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. Use market_report instead for the full measured breakdown; research_capability for market plus shortlist in one call; price_benchmark to judge a specific price.
Annotations the server declares
- title: Find a market
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
get_custom_benchmarkGet 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 ar…No findings
Why it is in this group
- The name "get_custom_benchmark" says "get": a word for reading.
Description, as the server wrote it 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.
Annotations the server declares
- title: Get custom benchmark
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
get_group_fair_priceGives the broad group-wide fair price for a kind of product: the median entry monthly price per buyer tier across its whole product group.No findings
Why it is in this group
- The name "get_group_fair_price" says "get": a word for reading.
Description, as the server wrote it Gives the broad group-wide fair price for a kind of product: the median entry monthly price per buyer tier across its whole product group. Use this when you want a general price guide: give a task or product type (or a group_id from the group price league) and get the fair price for each buyer tier (individual, pro, team / small business, enterprise) with its typical range, the group's typical payment models (free, subscription, usage, one-time, contact sales), usage and one-time medians where at least 3 listings publish them, and the group's 90-day price-index change. Groups are built from what products do, not from price. Medians of current published prices only; individual listings are not returned. Call with no arguments to list group IDs. Use price_benchmark instead to check a specific quote against the closest comparables; search_providers for candidates.
Annotations the server declares
- title: Get group fair price
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
get_price_indexUse when asked whether prices of AI agents, tools or MCP servers are rising or falling overall.No findings
Why it is in this group
- The name "get_price_index" says "get": a word for reading.
Description, as the server wrote it 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 chained quoted-price index of observed agent and MCP pricing in US dollars (changes in the publicly quoted price of the same product and offer; base 100 = 30 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). Every response names its release_id, reference_currency and methodology_revision; response_mode=full adds fx_attribution (exact native-price and exchange-rate contributions per window: log changes add, level factors multiply) and currency_evidence. 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.
Annotations the server declares
- title: Get price index
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
get_price_index_historyUse to show how AI agent and MCP prices have moved over time: the dated Agent Economy Price Index series, the same chained quoted-price series (US dollars, base 100 = 30 Jun 2026) …No findings
Why it is in this group
- The name "get_price_index_history" says "get": a word for reading.
Description, as the server wrote it Use to show how AI agent and MCP prices have moved over time: the dated Agent Economy Price Index series, the same chained quoted-price series (US dollars, base 100 = 30 Jun 2026) agentery.com/aepi charts. Points are index levels, never prices; calendar days with no published observation are listed in gaps with their reason, never interpolated. 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 per-day native / FX / combined components and the window's exact attribution). 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.
Annotations the server declares
- title: Get price index history
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
get_providerFor 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:…Reads private dataNo findings
Why it is in this group
- The name "get_provider" says "get": a word for reading.
What it can reach
- private-dataThe description's first sentence says "directory": it reads files.
Description, as the server wrote it 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.
Annotations the server declares
- title: Get provider details
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
get_provider_profileUse 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 / u…Reads private dataReads text others writeNo findings
Why it is in this group
- The name "get_provider_profile" says "get": a word for reading.
What it can reach
- private-dataThe description's first sentence says "doc": it reads documents.
- untrusted-inputThe description's first sentence says "website": it reads web pages, which anyone can write.
Description, as the server wrote it 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.
Annotations the server declares
- title: Get provider profile
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
get_researchStatus and result of a research job created by request_research.No findings
Why it is in this group
- The name "get_research" says "get": a word for reading.
Description, as the server wrote it 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.
Annotations the server declares
- title: Get research result
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
market_gapsFinds jobs callers ask for that few paid products serve: requests seen on this MCP server, clustered by meaning, that sit far from any paid provider.No findings
Why it is in this group
- The description's first verb is "find": a word for reading.
Description, as the server wrote it Finds jobs callers ask for that few paid products serve: requests seen on this MCP server, clustered by meaning, that sit far from any paid provider. Use this when a seller or investor asks where under-served opportunities are. Returns 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. Use demand_signals instead when you want searches that returned no or only weak results.
Annotations the server declares
- title: Find market gaps
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
search_providersFinds products (AI products, AI agents, MCP servers or APIs) that do a task and returns a ranked shortlist; start here to choose a product.No findings
Why it is in this group
- The name "search_providers" says "search": a word for reading.
Description, as the server wrote it Finds products (AI products, AI agents, MCP servers or APIs) that do a task and returns a ranked shortlist; start here to choose a product. Use this when someone wants candidates, e.g. 'MCP server to reply to Zendesk tickets'. Each result has what it 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: open strong ones with get_provider_profile, compare finalists with compare_providers. Thin coverage returns no_match, never padding. Use research_capability instead for a one-call overview with prices; price_benchmark, find_market or get_group_fair_price when the question is cost.
Annotations the server declares
- title: Search providers
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
suggest_alternativesFind 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, c…Reads private dataReads text others writeNo findings
Why it is in this group
- The description's first verb is "find": a word for reading.
What it can reach
- private-dataThe description's first sentence says "find" and "doc": it reads documents.
- untrusted-inputThe description's first sentence says "find" and "website": it reads web pages, which anyone can write.
Description, as the server wrote it 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).
Annotations the server declares
- title: Find provider alternatives
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.
Exfil surface
Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.
No private-data, untrusted-input, outbound path in this server alone: no tool is tagged outbound.
- Reads private data3
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write3
- Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
- Can send data out0
- Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.
Remote posture
What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.
Looked at Nov 20, 2026, 18:33 UTC, unchanged since Nov 6, 2026. No credentials were sent and no tool was called. What is looked at.
- Reachable
- yes
- HTTP status of an anonymous initialize
- 200
- tools/list served without credentials
- yes
- Tools that change things, listed without credentials
- 10
- Protocol version
- 2025-06-18
- WWW-Authenticate on 401
- not observed
- resource_metadata in WWW-Authenticate
- not observed
- RFC 9728 protected resource metadata
- not observed
- Authorization servers
- not observed
- Legacy HTTP+SSE transport
- no
- Dynamic client registration
- not observed
- Client ID metadata documents
- not observed
- HighThe whole server
The endpoint served tools/list without credentials, and the list has 10 tools that change things (4 destructive, 6 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://agentery.com/api/mcp: tools/list returned 23 tools to an anonymous client, including stop_research_updates (destructive), refine_results (destructive), update_custom_benchmark (destructive), delete_custom_benchmark (destructive), research_capability (write) and 5 more
Posture changes
- Nov 6, 2026
- Tools that change things, listed without credentials: 11 to 10
- Protocol version: 2025-03-26 to 2025-06-18
Findings
Matches of fixed checks, with the text they matched.
No check matched anything in these tool definitions. That is not a safety guarantee.
History
Changes to its tool definitions and to its remote endpoint, newest first.
PostureRemote posture changed. Tools that change things, listed without credentials: 11 -> 10; Protocol version: 2025-03-26 -> 2025-06-18.View diff
- Tools that change things, listed without credentials: 11 to 10
- Protocol version: 2025-03-26 to 2025-06-18
Tools2 changed.~2 changedView diff
- Changed:get_price_indexOnly readsdescriptioninputSchema
- Changed:get_price_index_historyOnly readsdescriptioninputSchema
Tools8 changed.~8 changedView diff
- Changed:demand_signalsOnly readsdescription
- Changed:find_marketOnly readsdescription
- Changed:get_group_fair_priceOnly readsdescription
- Changed:market_gapsOnly readsdescription
- Changed:market_reportChanges thingsdescription
- Changed:price_benchmarkChanges thingsdescription
- Changed:research_capabilityChanges thingsdescription
- Changed:search_providersOnly readsdescription
Tools4 changed.~4 changedView diff
- Changed:demand_signalsOnly readsinputSchema
- Changed:market_gapsChanges thingsinputSchema
- Changed:stop_research_updatesDeletes or cancelsinputSchema
- Changed:update_custom_benchmarkDeletes or cancelsinputSchema
Install
Pinned to version 1.28.2. Values in angle brackets are yours to fill in.
claude mcp add --transport http agentery https://agentery.com/api/mcpclaude mcp add --transport http agentery https://agentery.com/api/mcpRun in a terminal.
Claude Code permissions
Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.
{
"permissions": {
"allow": [
"mcp__agentery__search_providers",
"mcp__agentery__find_market",
"mcp__agentery__compare_providers",
"mcp__agentery__get_price_index",
"mcp__agentery__get_research",
"mcp__agentery__get_group_fair_price",
"mcp__agentery__get_price_index_history",
"mcp__agentery__market_gaps",
"mcp__agentery__suggest_alternatives",
"mcp__agentery__demand_signals",
"mcp__agentery__get_provider_profile",
"mcp__agentery__get_provider",
"mcp__agentery__get_custom_benchmark"
],
"ask": [
"mcp__agentery__research_capability",
"mcp__agentery__price_benchmark",
"mcp__agentery__request_research",
"mcp__agentery__report_outcome",
"mcp__agentery__market_report",
"mcp__agentery__create_custom_benchmark"
],
"deny": [
"mcp__agentery__stop_research_updates",
"mcp__agentery__refine_results",
"mcp__agentery__update_custom_benchmark",
"mcp__agentery__delete_custom_benchmark"
]
}
}Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as agentery. Review it before you use it.
Capability tags behind 4 rules
- mcp__agentery__request_research untrusted-input
- mcp__agentery__suggest_alternatives private-data, untrusted-input
- mcp__agentery__get_provider_profile private-data, untrusted-input
- mcp__agentery__get_provider private-data
Pin
Keep the decision: fail CI when the tools change, follow every change, or show a badge.
Pin in CI
Fail a build when the tools you reviewed are not the tools the server serves today.
curl -s "https://radar.anlyon.com/api/v1/servers/com.agentery/agentery/verify?hash=1ce8cce4f3e8f8bcd97aa113e788b344c6c091e93f6f550433d6be2b334b5ecb" | jq -e '.changed == false'Pinned hash 1ce8cce4f3e8, from Nov 15, 2026, 04:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/com.agentery/agentery/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/com.agentery/agentery)Source: MCP Registry · repository. Synced Nov 2, 2026, 01:17 UTC.
Agentery MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the Agentery MCP server safe?
- No scan can promise that. What its definitions show: 23 tools, 10 of which can change, send or delete something, and 0 findings from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.
Can the Agentery MCP server delete data?
- Yes. 4 tools can delete, cancel or revoke something: stop_research_updates, refine_results, update_custom_benchmark and delete_custom_benchmark.
Can the Agentery MCP server do things that cannot be undone?
- No tool is classed as irreversible: none of them sends, pays, publishes or merges, going by their definitions.
What tools does the Agentery MCP server have?
- 23 tools: 4 destructive, 6 write, 13 read. stop_research_updates, refine_results, update_custom_benchmark, delete_custom_benchmark, research_capability, price_benchmark, request_research, report_outcome and 15 more.
Does the Agentery MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the Agentery MCP server send data to outside services?
- None of its tools sends, posts or publishes, or takes a recipient, channel or URL.
Has the Agentery MCP server changed its tools?
- Yes, 3 times since Anlyon Radar started tracking it, most recently on Nov 1, 2026. Every change is on this page and in its Atom feed.