"Writing about MCP" matching MCP tools:

• leave_feedbackA

  AgentMarketplaceA

  Leave feedback about AgentMarketplace itself — bugs, confusing tools, feature requests. This is for feedback about the platform, not about a counterparty. There is no reputation or rating system here — that lives in AgentTrust. Args: access_token: AgentAuth bearer token (requires ``market.read``). message: Free-text feedback, up to 2000 characters. Returns: ``{"recorded": true}`` on success.

  ConnectorNo auth

• create_extractorA

  Extend MCPA

  Create a saved, reusable extractor (extract group). Three starting points, mutually exclusive: config (inline schema — call get_documentation with https://docs.extend.ai/extraction/schema.md BEFORE writing one by hand), cloneExtractorId (copy another extractor's draft config), or generate (Extend writes the schema from 1-5 sample documents plus optional instructions; no docs needed); name alone creates an empty draft. The draft is the only mutable surface — edit it with update_extractor, freeze it with publish_extractor_version, run it with extract_data.

  ConnectorOAuth

• update_sceneA

  AtriumKitA

  Changes one scene directly (free, instant): its variable values (merged; the ids and current values are in get_video — text, colors, numbers, images as "asset:<key>"), label, intent, duration (600–30000 ms; keep it at least as long as its narration), transition into it, narration script (null removes it), or its whole HTML (≤ 60000 characters, following the authoring rules from list_video_blocks; its variables are re-read from it). Changing the script makes its narration stale: then call generate_video_voiceovers. To change how a scene looks or moves, ask write_scene instead of writing HTML. Requires: demos:read, demos:write.

  ConnectorOAuth

• check_textA

  WSC - Writing Style CheckerA

  Analyze text for writing style issues: weasel words, passive voice, duplicate words, long sentences, nominalizations, hedging, filler adverbs, and research-cited AI tells. Read-only and stateless — text is analyzed in memory on the hosted server and never stored. Returns a plain-text report with each issue's line and column, the matched text, surrounding context, and the reason for AI tells; texts over 100,000 characters return an error message. This hosted server has no filesystem access — the wsc-mcp npm package adds a check_file tool for local files. It only reports issues — to auto-remove duplicate words, follow up with fix_duplicates.

  ConnectorNo auth

• cti_get_guidelinesA

  website-searchA

  Get Lenny Zeltser's expert CTI writing guidelines. Topics include tone, words, structure, executive_summary, voice, articles, summary, brief (one-page brief section guidance), handoffs (cross-server routing), methodology (the three subsections), fields (per-field guidance), and CTI-specific topics: attribution (full Six Signals prose), confidence (ICD-203 ladder), pyramid_of_pain, six_signals (signals table only), and anti_patterns. The general writing topics (tone/words/structure/executive_summary) now defer to `get_security_writing_guidelines` for the canonical Five Elements rules; CTI-specific content lives in the other topics. Pair the 'fields' topic with field_id for single-field guidance. This server never requests your campaign or threat-intel notes and instructs your AI to keep them local—templates and guidelines flow to your AI for local analysis.

  ConnectorNo auth

• adcritter_get_platform_overviewA

  AdCritter for BuildersA

  Start here. Returns the AdCritter platform overview - what AdCritter is, the entity hierarchy (organization > advertiser > campaign > ad), the happy path for getting ads running, and how to navigate the other MCP tools. Applications built from this guidance are REST API clients that call /v1/ endpoints, not MCP tool callers. Before writing code, call adcritter_get_api_reference(entity, action) for each entity and action you plan to use - tool descriptions and parameter names describe conceptual behavior only, and do not match actual API routes, field names, query parameters, or response shapes.

  ConnectorNo auth

• check_textA

  Writing Style CheckerA

  Analyze text for writing style issues: weasel words, passive voice, duplicate words, long sentences, nominalizations, hedging, filler adverbs, and research-cited AI tells. Read-only and stateless — text is analyzed in memory on the hosted server and never stored. Returns a plain-text report with each issue's line and column, the matched text, surrounding context, and the reason for AI tells; texts over 100,000 characters return an error message. This hosted server has no filesystem access — the wsc-mcp npm package adds a check_file tool for local files. It only reports issues — to auto-remove duplicate words, follow up with fix_duplicates.

  ConnectorNo auth

• concord_lemmaA

  orthotomeoA

  Complete-or-fail concordance: every words row in corpus whose lemma, dStrong, or (with by="surface") exact inflected surface form matches query. Route lemma/Strong's-number/surface-word lookups here, never by writing SQL or guessing occurrences from memory. This deployment caps one concordance result at 2000 occurrences and refuses anything broader, reporting the exact match count in the error. Call count first when a query might be broad - count is never capped.

  ConnectorNo auth

• update_load_test_notesA

  LoadsterA

  Replace the notes on a finished Load Test's Test Report — the only thing on a Load Test this surface edits. Ask the user before writing: notes belong to the user, and advising on a test never requires writing them. The text sent becomes the report's entire notes, so first read the current notes with get_load_test_report and preserve the user's content in what you send.

  Connector

  Destructive

  OAuth

• list_research_reportsA

  Onvexia: Crypto Fundamentals, Sentiment & Onchain TrackingA

  List the assets that currently have a generated research report available. Returns the index, not the reports — call get_research_report with a symbol for the body. An asset missing from this list has not been written up; that is a statement about our coverage, not about the asset.

  ConnectorNo auth

• gunspec_api_operationA

  GunSpecA

  Returns what the GunSpec API reference documents for an endpoint: its parameters and accepted values, the plan it needs, whether a key is required, caching, every error status with the error.reason values to branch on, and the languages a sample is printed in. Use this tool before writing or explaining code that calls the GunSpec API, instead of recalling parameters. The path may be a template (/v1/firearms/{id}), a concrete path or a URL; a partial path such as /v1/vendor lists the operations under it.

  ConnectorAPI key

• tag_contactsA

  SendingA

  Applies a tag to one or more contacts (max 100). Get the `tagId` from list_tags (or from create_tag for a new one). Idempotent: contacts already tagged are ignored. Each application emits the contact.tag_added event: use list_automations to see which automations listen to that event before writing.

  ConnectorAPI key

• crypto_reportA

  EventTrader MCPB

  A short research report on what a link or a topic means for one coin, grounded in the coin's dashboard, with its own public page to share. To ask: pass symbol and about (a public http(s) link such as a post on X, a press release or an article, or a topic of 3 to 300 characters); the answer comes at once with status=writing and the report's id. To read: pass report_id (no key needed); status is writing, ready or unavailable. At most 6 reports an hour and one a minute. The report is written by EventTrader's AI and can be wrong. Asking needs a registered agent (API key). From EventTrader's crypto dashboards (cymetica.com/crypto). Every number carries its source and time; a number that failed a plausibility check is withheld, never guessed. Places no orders, moves no funds. Not financial advice.

  ConnectorNo auth

• add_keywordsA

  AppTail – ASO & Keyword ResearchA

  Start tracking search terms for one of your apps, in one storefront. Send terms, or `keyword_ids` for suggestions returned by discover_keywords — a suggestion MUST be added by id, because re-resolving its term can land on a different keyword row. Counts against the plan's per-app keyword limit; `dry_run` reports what would happen without writing anything. Terms already in the corpus come back under `already_tracked` rather than as an error — that is the state the caller asked for.

  ConnectorNo auth

• xcut_find_outliersA

  XCut AI – Viral Content ResearchA

  Use this when the user asks which of a creator's, competitor's or their own posts performed best or beat the account's normal, or what works for an account before writing. Scores the latest 20, 30, 50 or 100 posts against that account's own median and says by how much each beat it. About 3-4 credits for 30 posts on Instagram or TikTok, none on YouTube, more on Facebook. Longer runs return a `job_id` for xcut_get_job. Do not use for a full metrics table (use xcut_profile_analytics) or for a topic across many accounts (use xcut_search_viral).

  ConnectorNo auth

• write_pageA

  SumibakoA

  File a Markdown document into the user's vault as a page, creating it or updating an existing one. This replaces the whole page, so use edit_page instead to change part of one. Returns the page and a link to it. Set externalId to a stable key for this artifact, such as the source file's path in the repository, so that writing it again updates the same page rather than adding a second copy. The previous version is kept for 14 days and the owner can restore it.

  ConnectorOAuth

• sw_listA

  Star Wars API & MCP server (swapi.build)A

  Lists every entity of one Star Wars resource type as a JSON array (Episodes I-VI data). Responses are large (all 82 PEOPLE, about 38 KB); to find a single entity, prefer sw_search, then sw_get; for a compact index pass fields, e.g. ["name"] (about 5 KB).

  ConnectorNo auth

• setThreadReplyingA

  NextmailB

  Tell the team you are writing a reply to an email thread, so getThreadTeam and the app show the others that you are replying and nobody answers twice. The mark lasts 30 seconds, so call it again while you are still writing, and with replying false once you have sent the reply or given up.

  Connector

  Destructive

  OAuth

• get_brand_instructionsA

  A1 LaneA

  Use before writing or rewriting a caption for this workspace, or when the user asks what the brand allows. Returns the workspace's stored brand instructions: approved claims, prohibited phrases, caption style and defaults (hashtags, call to action, links), as the workspace's owners and admins saved them in A1 Lane. Write from these instead of guessing or relying on earlier chat. Empty fields mean nothing is set. It changes nothing; A1 Lane does not enforce these on posts.

  ConnectorOAuth

• get_shop_infoA

  ARVI Wine CatalogA

  Facts about the merchant ARVI SA plus live catalog statistics: currency, contact, how a purchase is completed, the 48-hour delivery commitment across Switzerland, how the wines are transported and stored, and the sourcing service for bottles not currently in stock. Call it once when the user asks about the shop itself, about shipping, storage or provenance, or whether ARVI can find a wine that is not listed as available.

  ConnectorNo auth

• show_roomsA

  Roomza Hotel IntelligenceA

  REQUIRED whenever you present rooms. Whenever you are about to mention, recommend, or describe one or more specific rooms to the user, you MUST call this tool with those room UUIDs INSTEAD of writing the rooms in text. This is mandatory even when there is only ONE matching room — show it as a single hero card, never describe a lone room in prose. Call this BEFORE writing any prose about the rooms; the cards must appear first, then a brief summary. Pass room UUIDs (from get_hotel_rooms or search results) in ranked order, best first, 1 to 8 rooms. ALWAYS pass check_in and check_out when you know the user's dates: card prices are then for those exact dates. Without dates, cards show a typical from-price that can differ a lot from any specific dates. Each card shows photo, Roomza score, view, bed, and price. NEVER ask the user whether they want to see cards or images — just call this tool. When get_hotel_rooms returns no tracked rooms (a roomTypes list instead), call this with hotel_id and no room_ids: it renders the hotel's bookable room types as cards with photos and prices, each linking straight to booking.

  ConnectorNo auth