Read-only agent radar, weekly editions, sourced guides, scenario choices and revision sync.
Scored across 11 tools
Each tool targets a distinct retrieval pattern (by ID, by date, by cursor, by latest, by editorial type, by source, by workflow), and descriptions explicitly disclaim overlap. Minor confusion remains between the several content-reading tools (get_latest vs get_daily vs get_observations) and between choose vs compare, both of which operate on product dossiers.
All tools share a uniform botclaw_ prefix and the dominant convention is get_<noun> (8 tools), which is predictable. The deviations are choose, compare, and search, which are bare verbs rather than the get_ pattern, but they are still readable and consistent in spirit.
11 tools is well within the ideal range and each maps to a clear access or evaluation need. No redundant or filler tools are apparent.
The read-only observer surface is thorough: catalog, item, daily, latest, observations, changes stream, sources, workflows, search, plus choose/compare for evaluation. It is a deliberately read-only server, so the absence of write operations is by design, though there is no explicit bulk or batch fetch beyond paging.
Apply deterministic task, hosting, platform, budget and access gates to published dossiers. Each candidate has sourced reasons, explicit unknowns and hosting conflicts. No performance scores, account-access guarantee, inference, purchase or setup action. no-new-subscription does not establish free inference.
Inputs: task, access, budget, hosting, +2 more. Returns: _trust, inputs, choices, language, +2 more
Compare source-backed capabilities and explicit unknowns for the seven products. Filters can shortlist documented self-managed options. This is official documentation, not a tested product ranking or current account-access guarantee.
Inputs: language, products, selfHosted. Returns: _trust, evidence, language, profiles, +2 more
List the seven tracked products, category and content-type IDs, and the public MCP's paging and language options. Use these IDs in other tools.
Inputs: language. Returns: _trust, maxPage, language, pageSize, +6 more
Read a sequence-ordered change stream after a decimal cursor. Start at 0, persist nextCursor only after applying the page, and continue while hasMore. Upserts contain the current published projection; withdrawn events contain only ID/revision/date, item=null. Remove withdrawn records locally. Replaying a page is safe. This is not a historical full-text archive.
Inputs: limit, cursor, language. Returns: _trust, cursor, changes, hasMore, +2 more
Read public items dated on a real YYYY-MM-DD calendar day in Asia/Shanghai. Omit date for today. This is a date index, not an AI-generated daily report. reviewedAt is a source-review date, not a publication date. Returns 20 items per page.
Inputs: date, page, product, language. Returns: date, kind, page, items, +7 more
Read one published record by stable ID, with body, applicable conditions, evidence type, revision and canonical citation URL. Missing or withdrawn records return item=null. Original-source excerpts are not independent execution evidence.
Inputs: id (required), language. Returns: item, _trust
Read the latest dated agent news, newest first. Defaults to news; choose content_type guide, experience or review for other reading. Filters are listed by botclaw_get_catalog. Results have 20 items per page; use hasMore and page to continue.
Inputs: page, product, category, language, +2 more. Returns: date, kind, page, items, +7 more
Read published bilingual version radar, weekly editions, question guides or product dossiers. Includes full bodies, source dates, review dates and weekly coverage cutoff. Editorial interpretation is not product execution. Use product to include records discussing that product, including multi-product guides.
Inputs: q, page, product, section, +1 more. Returns: page, items, total, _trust, +4 more
List public source URLs, source origin (official or independent), collection state, last successful collection, and item counts. Manual sources are editorially reviewed; they are not automatic collectors.
Inputs: product, language. Returns: _trust, counts, sources, language, +2 more
Find owned, reproducible workflow procedures. Each list entry has a stable ID; call get_item for the steps and actual verification boundary. Only the Node RSS example currently has execution evidence. Does not run workflows.
Inputs: q, page, product, language. Returns: date, kind, page, items, +7 more
Search published titles, summaries and owned workflow text using bounded bilingual keyword aliases (1–80 characters). Product, content type and category filters apply. Returns up to 20 records per page, not a generated answer or live-internet search. Use get_item to inspect conditions, evidence and citation URLs.
Inputs: q (required), page, product, category, +3 more. Returns: date, kind, page, items, +7 more
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Trend data, an interactive Trend Radar and ad-targeting dry runs for AI agents. Read-only.
Media workflows, research and code for agents. Search sources, compare evidence and collaborate.
Agent-only long-form publishing: articles, notes, replies and follows under the agent's own byline.
Agent community: public cases, practical tasks, live policy and optional self-key participation.
Add one secure layer between your agents and this server.