"Tools or methods for keeping track of a conversation" matching MCP tools:

• music_chatA

  openFlowB

  Talk to the Google Flow Music Producer agent instead of one-shotting a track. Use this when the work is a conversation rather than a single brief: asking what it can do, having it write lyrics first, or editing a track it already made ("drop the vocals", "same song, 30 seconds shorter", "make the chorus bigger"). For a plain "make me a song about X", music_generate is the shorter path. message — what to say. conversation_id — omit on the first message, then pass the one that comes back so the Producer keeps its memory of the track. model — same choices as music_generate. Returns {"conversation_id", "text", "suggested_actions", "clips": [...], "media": [...]}. `text` is the Producer's reply. `suggested_actions` are the follow-ups it offers — show them to the user, they are good prompts for the next turn. `clips` is EMPTY when the Producer only talked, and filled when it decided to actually make audio; treat a filled `clips` exactly like a music_generate result and save the audio. A reply is usually seconds, but a turn that produces a song takes minutes and comes back as a job_id to poll with check_job.

  ConnectorNo auth

• invoke_mtprotoA

  Fast MCP TelegramA

  Low-level Telegram API (MTProto) invoke for methods not wrapped by other tools. Dangerous methods require allow_dangerous=true. Success: API result dict or normalized error. PII and credential-shaped fields (phone, access_hash) are dropped from a successful result by default; pass include_sensitive=true for the raw payload. A bare message id needs a chat binding: requests with no peer field (messages.GetMessages, messages.DeleteMessages) are refused, because a bare id resolves against an arbitrary dialog. Use channels.GetMessages or messages.GetHistory, which carry the binding. messages.GetHistory cannot address a forum topic (no thread_id/top_msg_id in the schema, and channels.GetHistory does not exist) -- use messages.Search with top_msg_id, or the high-level get_messages with reply_to_id. Full documentation: https://github.com/leshchenko1979/fast-mcp-telegram/blob/main/docs/Tools-Reference.md

  Connector

  Destructive

  No auth

• invoke_mtprotoA

  fast-mcp-telegramA

  Low-level Telegram API (MTProto) invoke for methods not wrapped by other tools. Dangerous methods require allow_dangerous=true. Success: API result dict or normalized error. PII and credential-shaped fields (phone, access_hash) are dropped from a successful result by default; pass include_sensitive=true for the raw payload. A bare message id needs a chat binding: requests with no peer field (messages.GetMessages, messages.DeleteMessages) are refused, because a bare id resolves against an arbitrary dialog. Use channels.GetMessages or messages.GetHistory, which carry the binding. messages.GetHistory cannot address a forum topic (no thread_id/top_msg_id in the schema, and channels.GetHistory does not exist) -- use messages.Search with top_msg_id, or the high-level get_messages with reply_to_id. Full documentation: https://github.com/leshchenko1979/fast-mcp-telegram/blob/main/docs/Tools-Reference.md

  Connector

  Destructive

  No auth

• edit_sessionA

  KeyboardiaA

  Make one narrow, retry-safe edit to an existing collaborative session. After every attempt, the next Keyboardia call must be get_session for the same session. A successful call includes a backwards-compatible compact snapshot plus an acknowledgement. That snapshot is not authoritative verification; do not make another edit or finish from it. Read with get_session next. Supported operations: add_track, set_track_instrument, set_track_pan, set_steps, and set_tempo. set_steps changes only the named steps; it never replaces a track or session. set_track_instrument replaces only a track's sound source, keeping its pattern, mix, timing, and custom name.

  Connector

  Destructive

  No auth

• search_d365_codeA

  ALM X++ MCP ServerA

  WHEN: object name is unknown, partial, or you need to find by concept/keyword. Search the D365 F&O knowledge base for X++ code, tables, classes, forms, views, enums, EDTs, security objects using natural language or partial names. Returns ALL chunks (metadata, Declaration, methods) for the top-scoring objects so the LLM has complete context on the first call. Lower-scoring results return a short preview. No follow-up get_object_details call is needed for top results. NOT for listing all objects in a model -- use list_objects for that. NOT when the exact name is known -- use get_object_details for that. NEVER call search_d365_code twice in the same conversation turn. If one search did not find the object, answer from what you have -- do not repeat the search. When you need context on MORE THAN ONE concept simultaneously, use batch_search instead -- it runs all queries in parallel and is faster. NEVER call for ADO items (FDD, RDD, IDD, Bug, Task, PR, WorkItem, sprint, #1234) -- use ado_* tools instead.

  ConnectorNo auth

• send_agent_messageA

  Fine StructureB

  Talk to an existing agent or assign it work using its normal tools, memory, permissions and team. Omit conversation_id to start a new owner conversation; supply it to continue one. Returns acceptance and a durable task_id immediately, NOT a completed answer. Poll get_agent_task and read get_agent_conversation for the actual response. Work continues after MCP disconnects. A follow-up in a busy conversation uses the normal queue. Customer conversations are readable but cannot be impersonated by this tool.

  Connector

  Destructive

  No auth

• studio.delete_elementsA

  Simpler.AsiaC

  Delete several scenes, timeline clips, stickers and captions in one edit: pass 1 to 200 ids in element_ids. All or nothing: an unknown id, a clip on a locked track, or a locked track a scene's cut would move refuses the whole call, names the first offender, and deletes nothing (unlock it with lock_track, or pass ripple_secondary "none"). Scenes follow ripple_secondary as in delete_element: "shift" (default) removes each deleted scene's time from every lane, keeping later clips in sync; "none" closes the main track alone. The receipt's clips_removed and clips_trimmed count each unlisted clip once, however many deleted scenes it spanned. Listed clips leave gaps (ripple_delete closes one); captions hide reversibly (restore_fillers brings them back).

  ConnectorNo auth

• recommend_toolsA

  RightAIChoice — verified AI tool dataA

  Use this when the user describes what they need an AI tool to DO rather than naming one — "something to transcribe interviews", "an image generator with an API", "a writing tool for a small team". Returns a verified shortlist matched on the described need, filtered by constraints the caller sets, and — unique to this catalog — screened against a survival bar: tools failing our link-health probes or scoring badly on the 5-signal viability model can be excluded outright. Each result carries its own health verdict, the date our record of it was last rebuilt, and pricing model. Matching combines meaning-based search (text embeddings of each listing) with keyword search over 8,000+ verified tools; the response states which methods ran. Tools with no viability measurement yet are listed separately by name rather than silently dropped. Not for: questions about a tool the user already named (use check_tool_status), head-to-head choices (use compare_tools), or filtering by price amount — prices are recorded verbatim in mixed currencies and are never converted or compared numerically.

  ConnectorNo auth

• category_landscapeA

  RightAIChoice — verified AI tool dataA

  Use this when the user asks what a whole category of AI tools looks like — how crowded it is, how healthy or risky it is overall, which tools in it are strongest, or which are in trouble. Examples: "how risky is the AI video generation market", "what does the code assistant category look like". Returns the number of tools we track in that category, how they distribute across survival bands, the category's vendor-link decay rate, and named examples at both the strongest and weakest ends — each with its own survival score and the date our record of it was last rebuilt. Categories are our own classification and tools belong to several at once, so category sizes overlap and never sum to the catalog total. Bands classify risk, not quality — the model has no notion of company size. Not for: choosing between named tools (use compare_tools), finding a tool for a job (use recommend_tools), or market-wide mortality statistics (use deadpool_digest).

  ConnectorNo auth

• recommend_toolsA

  RightAIChoiceA

  Use this when the user describes what they need an AI tool to DO rather than naming one — "something to transcribe interviews", "an image generator with an API", "a writing tool for a small team". Returns a verified shortlist matched on the described need, filtered by constraints the caller sets, and — unique to this catalog — screened against a survival bar: tools failing our link-health probes or scoring badly on the 5-signal viability model can be excluded outright. Each result carries its own health verdict, the date our record of it was last rebuilt, and pricing model. Matching combines meaning-based search (text embeddings of each listing) with keyword search over 8,000+ verified tools; the response states which methods ran. Tools with no viability measurement yet are listed separately by name rather than silently dropped. Not for: questions about a tool the user already named (use check_tool_status), head-to-head choices (use compare_tools), or filtering by price amount — prices are recorded verbatim in mixed currencies and are never converted or compared numerically.

  ConnectorNo auth

• category_landscapeA

  RightAIChoiceA

  Use this when the user asks what a whole category of AI tools looks like — how crowded it is, how healthy or risky it is overall, which tools in it are strongest, or which are in trouble. Examples: "how risky is the AI video generation market", "what does the code assistant category look like". Returns the number of tools we track in that category, how they distribute across survival bands, the category's vendor-link decay rate, and named examples at both the strongest and weakest ends — each with its own survival score and the date our record of it was last rebuilt. Categories are our own classification and tools belong to several at once, so category sizes overlap and never sum to the catalog total. Bands classify risk, not quality — the model has no notion of company size. Not for: choosing between named tools (use compare_tools), finding a tool for a job (use recommend_tools), or market-wide mortality statistics (use deadpool_digest).

  ConnectorNo auth

• handoff-to-humanA

  Chatway Live ChatA

  Request human-agent handoff for a Chatway conversation that is currently handled by a Chatway AI assistant. Returns an error if no AI assistant is assigned to the conversation; in that case, assign a teammate with `assign-conversation` or add a private note instead. This records a handoff request but does not guarantee that a human has joined or replied. Use it when the customer asks for a person or the request cannot be handled with the available tools; after handoff, do not reply with `send-message`.

  ConnectorOAuth

• broker_sync_prop_firmsA

  Wicked MCPA

  [Broker Sync API] Prop-firm platform integration registry — live-verified methods (Topstep ProjectX API, FTMO MatchTrader bridge) and connection status. Use when you want the registry of prop-firm platforms and which integration methods are live-verified. Not for a user's own accounts (use broker_sync_connections). Behavior: read-only. Priced via x402 (USDC on Base) or free with WICKEDAPI_API_KEY; with neither, you get HTTP 402 with the decoded price in payment_required (a price quote, not a failure).

  ConnectorNo auth

• studio.move_clips_to_trackA

  Simpler.AsiaC

  Move 1 to 200 timeline clips onto another track of the same kind (a b-roll clip to a video-broll track, a title to a text track, music to an audio-music track, a voice clip to an audio-voice track), keeping their spacing; delta_ms also moves them in time (default 0). Stacking follows the track: get_composition lists tracks in stacking order, and a clip on a later video-broll or text track draws over the earlier ones. All or nothing. Refuses, naming the first offender and moving nothing: an unknown clip id or track_id (get_composition lists the ids), a locked source or target track (unlock it with lock_track), a target of another kind (pick a track of the clip's kind, or add one with add_track), a target that would pass its clip cap (move fewer clips, or add a track with add_track), listed clips that overlap each other (move them one at a time), a clip pushed before 0 or past the timeline cap (keep delta_ms within the range the refusal gives), or a landing that overlaps a clip already on the target (use another delta_ms; the refusal gives the nearest one that fits).

  ConnectorNo auth

• read_perspective_statusA

  Perspective AIA

  Returns a server-computed health snapshot for a perspective: phase (design/test/share/live), outline state, conversation/completion counts, emoji feedback, insights count, enabled-automation rollup by kind, and workspace credit balance. Phase rules: - design: no outline yet - test: outline exists, no preview/test and no real participants - share: preview/test exists, no real participants yet - live: at least one real (NORMAL) conversation — always wins over test/share Behavior: - Read-only. - Errors when the perspective is not found or you do not have access. - insights_count includes drafts and published insights; use read_insights for the breakdown and read_insight for content. When to use this tool: - "Where does this perspective stand?" / status check before analysis or outreach. - Deciding whether to invite participants, dig into insights, or keep designing. When NOT to use this tool: - Aggregate volume breakdowns by period/trust — use perspective_get_stats. - Reading insight content or conversation transcripts — use the insight/conversation tools.

  ConnectorOAuth

• conversations_explorerA

  Perspective AIA

  Start a deep text exploration of conversation transcripts. Returns immediately with a job_id (status "pending"); long-poll perspective_await_job until status "ready" for findings with source citations. A sub-agent reads raw transcripts (exact phrases, multi-conversation patterns, deep reads). Prefer conversations_search for broad thematic/semantic questions, and conversations_data_analysis for quantitative counts. Omit filters to explore the full analysis corpus. Use filters only to establish a clear transcript boundary: conversation status, a creation-date range, or explicit conversation IDs. Use conversations_data_analysis first when a cohort must be identified from structured attributes, then pass the resulting conversation IDs here. A filtered job covers the complete filtered scope, not the complete perspective. Use for: - Exact mentions of words/phrases - Comparing conversation patterns across time - Reading full conversations with specific participants - Cross-referencing text patterns ("conversations mentioning X AND Y") - Interviewer approach or conversation flow Behavior: - Read-only against conversation data. - Open-world: runs an automated exploration agent in a durable background job using external services. - Each call starts a new job — not safe to retry blindly for the same query. - Typical flow: conversations_explorer → perspective_await_job (re-poll while pending). When NOT to use this tool: - Counts/distributions — use conversations_data_analysis. - Semantic themes without exact match — use conversations_search. - One known conversation id — use perspective_get_conversation. - Polling a previously-started job — use perspective_await_job.

  ConnectorOAuth

• t54_list_operationsA

  Agentic Swarm Marketplace (T54 x402 MCP)B

  Returns operationIds, HTTP methods, paths, and query parameter names from the bundled OpenAPI spec (no network). Use before t54_x402_request or per-SKU tools.

  ConnectorNo auth

• list_payment_methodsA

  agentcardA

  List the saved payment methods (used only to pay for flight bookings, not for cards or adding funds). Returns each method with its id, brand, last 4 digits, and expiry, and marks the default one. Use setup_payment_method to add a new one. The gated tools set_default_payment_method and remove_payment_method also exist; call them by name even though they aren't in the tools list.

  ConnectorNo auth

• dynomatix_aboutA

  DynomatixA

  Who Dynomatix is, what it sells and how to reach it. Returns the company's identity and tagline, its engagement types, both contact addresses, its key pages and its track record. Read this first if you are deciding whether this company fits a need; use dynomatix_submit_enquiry to start a conversation. Takes no arguments.

  ConnectorNo auth

• discoverA

  AgentMarketplaceA

  Discover AgentMarketplace's capabilities, tools, auth methods, and scopes. Call this first when connecting to AgentMarketplace to understand what's available and how to authenticate. No authentication required. Returns a catalog of available tools, resources, auth methods, and scopes.

  ConnectorNo auth

• video_editor_add_clipA

  ClipwaveA

  Place an existing LIBRARY asset onto a video's timeline by id (deterministic — use this instead of asking instruct to "add a clip"). Track is inferred from the asset kind when omitted: video AND image → video track (an image is shown as a still for duration_sec, default 1s, like a slideshow frame), audio → voice track. Optional position = 0-based index on that track (default appends to the end). Returns clip_id.

  ConnectorAPI key