"Creating the Best General-Purpose Agent" matching MCP tools:

• aws___search_documentationA

  AWS KnowledgeA

  AWS docs search. Each result's `context` is verbatim page text -- a real chunk of the actual page, not a short snippet -- and usually already contains the answer, so answer directly from it. Use `read_documentation` only when the chunks genuinely lack the needed detail. Pick ONE topic. Add a 2nd ONLY if query genuinely spans domains. Extra topics dilute ranking. - reference_documentation -- API/SDK/CLI specs, config params - current_awareness -- new/released/announced - troubleshooting -- errors, "how to fix" (NOT for conceptual/feature questions) - amplify_docs -- Amplify (+ language) - cdk_docs -- CDK concepts/guides - cdk_constructs -- CDK code samples, L3 - cloudformation -- CFN/SAM templates - strands_docs -- Strands Agents SDK (its Skills/agents concepts go here, NOT agent_skills) - agent_skills -- this tool's guided skills (load via `retrieve_skill`) - general (default) -- architecture, best practices, tutorials, feature behavior Results: rank_order (lower=better), url, title, context (verbatim page chunk -- answer directly from it).

  ConnectorNo auth

• create_api_keyA

  Molt2MeetA

  Generate a new API key for your agent. The full plaintext key (m2m_...) is returned ONCE — store it securely immediately; it cannot be retrieved later (we only keep its hash). Use keyName to identify the key's purpose (e.g. 'production', 'staging'). Multiple keys can be active simultaneously for zero-downtime rotation. Requires: an existing API key from register_agent. Next: switch your integration to the new key, then revoke_api_key on the old one.

  ConnectorNo auth

• get_project_memoryA

  QuillHubA

  Fetch the AI-maintained memory document for a project or workspace — the best single source for a handoff-style briefing. Sections include purpose, glossary, key people, activity digest, and routing signals, distilled across all meetings. Pass EXACTLY ONE of `project_id` (project memory) or `workspace_id` (workspace-level memory); get ids from `list_workspaces`. Returns the memory as rendered markdown plus `updated_at`. Start here for "give me a summary / bring me up to speed on project X" questions, then drill into `find_subjects`/`search_meeting_transcripts` for specifics.

  ConnectorOAuth

• search_titlesA

  QQuickpickA

  Find movies and/or TV shows that are genuinely available on a subscription streaming service in a specific country, filtered by score, genre, runtime, age rating, release year, country of origin, required cast members, notable people's own watch history, review tone, and similarity to a title the user already knows. All given filters combine with AND logic (except where noted). Use this instead of guessing streaming availability from general knowledge, which is frequently wrong or outdated -- catalogs change constantly and vary by country. Also use this tool for completely open-ended requests with no stated criteria at all, e.g. "suggest something to watch" or "I don't know what I want to watch" -- call it with just the country and no other filters to get QQuickPick's currently popular streamable picks, rather than answering from general knowledge alone. Movie results also carry a "facts" object (or null when unknown): Best Picture winner/nominee, Oscars won ("at least" -- the source is not exhaustive, so never state it as an exact count), festival top prizes, the work it is based on, and its franchise with all films in order. Use the awards / based_on_existing_work / franchise filters (movies only) to answer questions like "Oscar winners based on a novel I can stream tonight" or "all films of a franchise available to me". Use similar_to for "something like X" requests instead of guessing similar titles from general knowledge. Use origin_countries for requests like "an Asian film" or "a French series" -- do not guess specific titles from general knowledge for this. Each result includes a site_url (QQuickPick detail page) and, where available, a watch_link with required attribution -- include these links when presenting results to the user, not just the raw facts. The response also carries a top-level available_filters hint listing filters on this tool that were not used in this call -- consider offering ONE of them as a natural follow-up question, not all of them, and only when it fits the conversation.

  ConnectorNo auth

• update_inventory_productA

  QuailOSB

  Update a General Inventory product by productId or sku: name, SKU, ASIN, barcode, category, prices, manufactured flag and BOM (bomComponents replaces the whole BOM; hasBom:false clears it). Stock is changed only via adjust_inventory_stock. Supports confirm (false = dry-run preview).

  ConnectorNo auth

• meta-tools.searchA

  Vee3A

  Search live Vee3 agent tools by keyword or short task description. Call this first when you are unsure which tool to use. Returns ranked matches with tool_name, summary, and cost for each hit. Use meta-tools.describe on the best match for full request and response schemas. Optional group_id narrows results to one capability group. limit defaults to 8 (maximum 20). Cost = 0 tokens.

  ConnectorNo auth

• uk_car_tax_vedA

  Xearno ToolsA

  What you’ll pay to tax your car this year — the first-year bill on a new one, the £200 everyone pays after that, and the £440 surcharge on pricier cars. Car tax arrives as two very different bills. The first year is a one-off charge set by the car’s CO2, running from a few hundred pounds to over £5,000 — which is why it usually disappears into the on-the-road price and is forgotten. Every year after that is a flat £200, and electric cars have paid it since 1 April 2025, the single fact a general-purpose AI is most likely to get wrong. Then there is the surcharge: any car listed above £40,000 pays an extra £440 a year from its second year to its sixth. For EVs that threshold rose to £50,000 on 1 April 2026 and was backdated to anything registered from April 2025, so even an answer that was correct last year has gone stale. Cars from 2001 to 2017 run on an older CO2 table, which is here as well.

  ConnectorNo auth

• search_jobsA

  JobYap Job SearchA

  Search JobYap's aggregated job postings with structured filters. Fast (under a second): use it to browse, list, count or page through postings and to answer general questions about who is hiring. To find the best postings for one specific person (a resume, or their experience, skills or visa needs), use match_jobs instead. The text query matches job titles only (case-insensitive substring) — try synonyms or shorter tokens when results are thin. Company names must exactly match values from list_companies; locations must be identifiers from search_locations. work_mode matches jobs explicitly marked remote or hybrid (unmarked means unstated, not onsite). Results are active listings, newest first by default; sort=popular ranks by discussion activity. To paginate, pass next_cursor back as cursor and keep every other argument identical.

  ConnectorNo auth

• joinA

  ApuchatA

  Join a channel by id + token. Provide either a callsign (anonymous) or an identity_key (account-bound; callsign comes from the identity). If the channel has require_identity=true, identity_key is mandatory. If the human operator gave you an owner_password for the channel, pass it here — the server uses it to mark this session as 'human-authorized' and unlocks trusted-mode behavior. After joining, this session is bound to that channel — subsequent send/listen/roster/history/leave operate on it. PUBLIC BANDS: there are three always-on always-public channels — `general`, `help`, `random` — anyone can join without a token (token is ignored on these). Pass channel_id='general' (or 'help' / 'random') with any callsign. Useful for serendipitous agent discovery: when the user says 'unite a la banda general' or 'join the help band', go straight to join with channel_id='general' — don't ask for a token, don't create a new channel. SEE ALSO: if the operator wants to 'drive you from a phone' / 'send a pair link' / 'control you from their couch', do NOT just join — first call `open_remote_control` (for a new channel) or `make_remote_link` (to attach a phone link to a channel you're already in / about to join). Those tools mint the phone identity + mobile_url + owner_password in one go; plain `join` won't give you a URL the human can open on a phone. SWITCHING CHANNELS: from this unified endpoint you can `join` a different channel_id at any time — the session re-binds. No restart, no config edit, no new MCP install.

  ConnectorNo auth

• get_hero_pathA

  VA Heroes PH — From Zero to Hero | Become a Virtual AssistantA

  Retrieve the full published detail of one VA Heroes PH Hero Path, identified by its slug (for example 'general-va'), so an agent can explain that specific track to a visitor. Use it after get_hero_paths when the user asks about one track — what it covers, who it suits, or where to read more. Requires 'slug': the exact lowercase slug of an existing path; an unknown or misspelled slug returns a NOT_FOUND error that lists the valid slugs. Returns one record with slug, name, label, tagline, description, intro, highlights, type, featured, externalUrl and canonical url. It does NOT return pricing, schedules, enrolment or applicant data, and it cannot submit an application.

  ConnectorNo auth

• vote_feature_requestA

  AALYA

  Add one vote to an existing feature request — the 'me too' signal for something already filed, instead of creating a duplicate. Call once per distinct person/session you're voting on behalf of; there is currently no per-voter dedupe, so an agent must not call this repeatedly for the same requester to inflate the count.

  ConnectorAPI key

• post_forumA

  Voicescape — on-chain identity and tipping for AI agentsA

  Post to a Town Hall forum board AS YOUR REGISTERED AGENT BLOCKPAGE. TWO STEPS: (1) call without hcs_tx_id — validates everything (agent identity, board, rate limit, content safety) and returns the EXACT HCS JSON message plus the topic to submit it to; (2) sign that message with YOUR OWN Hedera key (the on-chain owner of your agent blockpage) and submit it to the topic yourself via the Hedera SDK (TopicMessageSubmitTransaction) — you pay the tiny HCS fee — then call again with the same arguments plus hcs_tx_id to confirm. Boards: general (default), tutorials, showcase, agents, ideas, help. agent-workshop posts go through post_agent_feedback instead; announcements is post-only for town hall moderators. Replies: pass reply_to with a post sequence number. Limits: 20 posts/day per agent (UTC). Content is safety-checked BEFORE you sign — blocked content never reaches the chain.

  ConnectorNo auth

• register_agentA

  LastPingA

  Requires the write scope or higher. Registers an autonomous agent in the project's agent registry and returns its id, slug and wire-up steps. One agent stands for one autonomous worker, which can own many monitors: create_monitor and update_monitor attach a monitor through agent_id (the id or the slug). An agent_id that does not exist is an error (400 UNKNOWN_AGENT), never an implicit create. The slug is derived from the name, so registering the same name again is refused (409) rather than creating a second agent.

  ConnectorAPI key

• create_folderA

  Scribe MailA

  Create a new, empty signature folder to organize signature templates. Folders created here are top-level (not nested). Use it only when no suitable folder exists: call list_folders first to reuse one, and use update_folder to rename an existing folder instead of creating another, since duplicate names are allowed. Creating a folder files nothing: to put a signature in it, pass the returned `id` as `folder_id` to create_signature or update_signature. Writes one folder and returns it with `signature_count` 0. Needs the folders:write scope; a blank name returns 422.

  ConnectorOAuth

• respond_contact_requestA

  netsiA

  Accepts, declines or blocks an incoming contact request. The person decides first: accepting lets that agent share invites, expenses and items. Declining stops them from asking again for 30 days; blocking is silent and permanent until you unblock by adding them. To block someone at any time, block_contact is the general tool.

  ConnectorNo auth

• helloA

  The Cure ProtocolA

  START HERE. One call that orients a new agent completely: the protocol, the live state of the research board, the single best piece of work to pick up with the exact call sequence, a resume cursor, and the published rate budget. Call this before anything else. NEXT: claim_work to announce what you are taking, or whats_new later to catch up.

  ConnectorNo auth

• create_groupA

  HomonoiaA

  Start a private group chat with several agents. Use it to negotiate or coordinate with more than one agent at once, such as several suppliers, or a buyer and a carrier. Starts a private group chat with you as its creator and the agents in `members` as its other members: up to 20 in all. Members read only the messages sent while they are in the group, so add them now, before you write. Later only you add and remove members (add_group_member), or invite agents with a link (create_invite); the others can propose agents to you. `members` may include your own address, which counts once. An unknown agent address in `members` is refused with 404. There is no idempotency key: if a call fails, check list_groups before creating the group again. Needs the personal token.

  ConnectorNo auth

• aetherwave_generate_imageA

  AetherWave StudioA

  Generates one or more images from a text prompt (T2I) or a text prompt + reference image(s) (I2I). Submits the job, polls until terminal, and returns the final image URLs. Default model is 'grok-imagine-t2i' (fast, 2 images per generation, 6 credits). Use list_image_models to see the full lineup with pricing. For I2I, pass `referenceImages` as an array of public image URLs and pick a model with I2I support (e.g. 'grok-imagine-i2i', 'wan-2.5-spicy-i2i'). ## Putting a UGC character in the image When the user names one of their characters ("put Amy in this T-shirt", "Cade Ellison from behind"), pass `character` with the name. The tool attaches that character's approved reference pack and identity text for you, and defaults the model to `gpt-image-2-t2i`. Put the product, garment or location in `referenceImages` as usual; describe the pose and framing in the prompt. Characters are the member's own creations, not third parties. Call `aetherwave_list_characters` if you need the names. ## Model selection guide (when the user does not specify a model) Default: `grok-imagine-t2i` (6 cr, 2 outputs per call, fast, general purpose). **Strong recommendation: when a single high-quality output is what's wanted** (most agent / one-shot workflows), prefer `gpt-image-2-t2i` (9 cr @ 1K / higher @ 2K, single deterministic image, best general quality across realism, illustration, typography, and composition; supports up to 2K resolution and most aspect ratios including auto). This is the front-runner for serious creative output where you don't need to pick from 6 variations. Pick a different model when the prompt has these signals: - "single best result" / "one image" / production / no time to pick from variations -> `gpt-image-2-t2i` (9 cr, 1 output, top general quality) - "photoreal" / "photo of" / "realistic" -> `gpt-image-2-t2i` (9 cr, best general realism), `nano-banana-2` (8 cr @ 1K), or `z-image-turbo` (2 cr, fastest) - "highest quality" / "premium" / no budget -> `gpt-image-2-t2i` at 2K (12 cr), or `grok-imagine-quality-t2i` (14 cr) - Text inside the image (signs, posters, typography) -> `gpt-image-2-t2i` (strongest lettering of the live models) - Album art / cover art -> `gpt-image-2-t2i` for one strong image; `grok-imagine-t2i` for 2 variations to choose from; `seedream-v4-t2i` if 4K wanted - Logo or design with embedded text -> `gpt-image-2-t2i` - NSFW / adult / explicit -> `wan-2.5-spicy-t2i` (auto-tags creation as 18+; routes to adult gallery) - Cheapest possible / quick test -> `z-image-turbo` (2 cr) - Multiple variations to compare -> keep `grok-imagine-t2i` (2 outputs per call) or `seedream-v4-t2i` with `maxImages` up to 6 For I2I (reference image provided): prefer the dedicated `aetherwave_edit_image` tool for "change something in this image" intent. Use `aetherwave_generate_image` with I2I models only when you specifically want style transfer, premium quality (`grok-imagine-quality-i2i`), or adult content (`wan-2.5-spicy-i2i`). Always pass an explicit `aspectRatio` (e.g. "1:1" for square album art, "16:9" for video thumbnails, "9:16" for shorts/reels). Some upstream providers reject submissions with no aspect ratio. Ask the user only when: - The prompt contradicts itself (e.g., "highest quality but cheapest") - The user requested "the best model" with no context, surface 2-3 options with tradeoffs - A single generation would cost more than 20 credits and the user has not confirmed Returns within ~45 s. If the result has state "running" the job is still rendering: poll aetherwave_get_job with the returned taskId and kind every ~10 s. Pass wait:true ONLY if your MCP client permits tool calls longer than 60 s (most do not). Pass async:true to get the taskId back immediately without waiting.

  ConnectorNo auth

• search_webA

  Salesbot - B2B outreach LinkedIn MCP Server with CRM and emailA

  Use for general web research (company info, news, job portals). For LinkedIn profiles use search_linkedin_people; to read one company's own site use read_company_website. General-purpose Google search — returns organic results for any query. Unlike search_google_xray (LinkedIn-only), this searches the entire web. Useful for finding job postings on portals (jobs.cz, prace.cz, profesia.sk, indeed.com), company info, news, or any other web content. Results are NOT saved to contacts — use this for research and discovery. Capped at 4 calls per minute to protect the Serper/Google budget.

  ConnectorAPI key

• kenwea.onboarding.registerSelfA

  Kenwea — Sandbox Attestation & Agent MarketplaceA

  Self-register as a new agent with no credential and no human. Send agentName (not name, which is ignored); declaredModel is optional and shown as your own claim, never verified. Returns a one-time API key and a pairing PIN. Use this first if you have no Kenwea key. The key can browse the whole market and run kenwea.sandbox.check immediately; selling, buying and bidding wait until a human operator claims you with the PIN. Operators creating an agent for themselves use kenwea.onboarding.startOperatorAgent instead.

  ConnectorNo auth

• dreamagent_list_global_integrationsA

  DreamAgent CloudA

  List the user's saved credentials (Global Integrations). ALWAYS call this before creating any bot project or asking the user for a token/API key. Saved credentials are referenced BY ID when creating projects: bot_token_integration_id for bot tokens, global_integration_ids for other keys. Secret values are never returned — only IDs and metadata (type, key name, verified, title). If nothing suitable is saved: direct the user to dreamagent.cloud → Settings → Global Integrations to add it (one-time, verified, reusable). Never ask the user to paste tokens in chat.

  ConnectorNo auth