Every change Wellknown observed on this MCP server, newest first, with what it was before and what it became. Tool-surface changes carry the definition diff. Nothing here is edited after the fact.
Changed the definition of "get_alternatives", "get_submission_status", "get_tool" and 6 more
List[Toolopen-sourcedirectory] Use this when you need alternatives to a known AI agent tool,withnotGitHublaunchstatsdirectories. Pass slug, the tool identifier returned by search_tools (foreachexample,todify),comparenotoptions.a URL or directory domain. Returns the source tool slug and its recorded alternatives with GitHub stats for comparison.
Check[Tool directory] Use this when checking the AgentoolRank review status of asubmissiontool(pending/approved/rejectedyou submitted via submit_tool. Requires submission_id and status_token from that submission; returns review status, queue position,and listing URL).when available. Not for launch-directory progress — that is my_progress.
[Tool directory] Get details for one tool by slug (from search_tools): GitHub stats, capabilities, best-for, limitations,and alternatives.
[Launch directories] Use this after report_result or to resume a session; requires the Submit Kit:everykey.directoryReturns product_type, cap, sites, progress_page and counts: issuedto(totalthishandedkeyout), unreported, submitted, listed_reported, rejected, failed anditsskipped.reportedOutstanding sites have status 'issued' in sites. Remaining allowance is cap minus issued,plusnotthea
Submit Kit[Launch(paid,directories]keyUserequired):thisgetwhentheworkingNEXTthrough launchdirectory to submit this product to, onedirectoriesatwith atime, ranked for the product type by our measured listing rate (listing_rate shows how many of the submissions we checked arerequiredlive,SubmitwithKitn
Which launch[Launch directoriesshould a product be submitted to? Returns sites our own products]actuallyUsewentthisthrough,wheneachyoutaggedneedautoa/freemanualoverview(needsofonethehumanbest-fit
Submit[LaunchKit:directories]reportUsewhatthishappenedwhenatrecording an outcome for adirectorydomainyouissuedgotbyfromnext_directory,next_directory.not submitting a tool to AgentoolRank. Requires the same Submit Kit key, that domain and status: submitted|
[Tool directory] Search open-source AI agent tools (frameworks, coding agents, memory, RAG, observability, MCPservers...servers) ranked by GitHub activity. Returns stars, 30-day ⟨5 unchanged words⟩
[Tool directory] List an AI agent tool (framework, coding ⟨58 unchanged words⟩
Added "my_progress", "next_directory" and "report_result"; changed the definition of "recommend_directories" (6 tools before, 9 now)
⟨46 unchanged words⟩ checklist of the human steps. Free: top10.5. With a Submit Kit key ($29 one-time): up to3050 sitesfortailored to the product type, handed out one at a time via next_directory, plus a "don't submit" list with reasons. ⟨11 unchanged words⟩
Submit Kit: every directory issued to this key and its reported status, plus the progress page.
Changed the definition of "recommend_directories"
⟨55 unchanged words⟩ a Submit Kit key ($29 one-time): up to 30 sites for the product type plus a "don't submit" list with reasons. ⟨11 unchanged words⟩
Certificate recorded, valid to 2026-12-29
Authorization not required
Unknown → Live
First tool surface recorded: 6 tools (server version 1.0.0)
https://agentoolrank.com/api/mcp (mcp_streamable_http) — from mcp_registry, with the record
Showing the latest 8 events. The API returns up to 500 and filters by kind: ?kind=tool_surface_changed
Submit Kit (paid, key required): get the NEXT launch directory to submit this product to, one at a time, ranked for the product type by our measured listing rate (listing_rate shows how many of the submissions we checked are live, with n and the verification date; small_sample when n < 3). Submit there, then call report_result before asking for more: at most 3 unreported sites at once, up to 50 per key. The product type is bound on the first call.
Submit Kit: report what happened at a directory you got from next_directory. status: submitted | listed | rejected | failed | skipped. A reported 'listed' is checked by our own daily listing check before it counts toward any listing rate.