"A server that supports Server-Sent Events (SSE)" matching MCP tools:

• stream_taskA

  TunnelMind Data APIB

  Opens a persistent SSE connection that emits events as the task progresses. The stream closes automatically when the task reaches a terminal state or after ~90 seconds (timeout). Heartbeat comments are sent every ~15 seconds to keep the connection alive through proxies. Event types: - `status` — emitted when status changes (pending → running → complete/failed) - `result` — emitted on `complete` with the full result payload - `error` — emitted on `failed`, `cancelled`, or `expired` with error info - SSE comment (`: heartbeat`) — keepalive, no data Use this tool when: - You want real-time progress without polling. - You are in an environment that supports SSE (EventSource API). Do NOT use this tool when: - You want a simple one-shot status check — use `get_task` instead. - Your HTTP client doesn't support streaming responses. Inputs: - `task_id` (path, required): 26-char ULID. Returns: - SSE stream (`text/event-stream`). Each event is `event: <type>\\ndata: <json>\\n\\n`. Cost: - Free. Counts as one request against rate limits when the stream opens. Latency: - First event: <200ms. Stream duration: up to 90s.

  ConnectorNo auth

• update_webhookA

  MailercloudB

  Update an existing webhook's configuration. Only the fields given (name, url, events) are changed: the tool reads the webhook first and resends its current values for the rest, since the API needs all three. events replaces the current set. Use toggle_webhook to enable or disable. Set dry_run: true to see the merged values that would be sent.

  Connector

  Destructive

  API key

• logistics.tracking.statusA

  apibaseB

  Get full tracking timeline for a registered package — latest status, all carrier scan events with timestamps and locations, delivery milestones, transit days, origin/destination countries. Supports 3,200+ carriers across 220 countries. Call tracking.register first if number is not yet registered (17TRACK)

  ConnectorNo auth

• volanea_create_workflowA

  VolaneaA

  Create an event-triggered automation workflow from a node/edge graph. Created as a DRAFT — verify it with volanea_test_workflow, then activate explicitly via volanea_update_workflow { status: 'active' }. Idempotent by name. Triggers: "event:<name>" (a product event sent to POST /v1/events or the volanea_track_event tool), "contact.created", "segment:enter:<segmentId>", "segment:exit:<segmentId>".

  ConnectorNo auth

• volanea_create_workflowA

  VolaneaA

  Create an event-triggered automation workflow from a node/edge graph. Created as a DRAFT — verify it with volanea_test_workflow, then activate explicitly via volanea_update_workflow { status: 'active' }. Idempotent by name. Triggers: "event:<name>" (a product event sent to POST /v1/events or the volanea_track_event tool), "contact.created", "segment:enter:<segmentId>", "segment:exit:<segmentId>".

  ConnectorNo auth

• watch_eventsA

  ctxstore — memory that follows you across modelsA

  Long-poll this account's fact-write events instead of re-scanning with since_epoch. Every store/supersede/delete/archive/restore/move publishes one event {key, id, namespace, layer, op, ts, seq}. One call waits up to max_wait_s (max 25) for the first matching event and returns up to 50, plus next_since. MCP has no streaming here, so loop: pass next_since back as `since` on the next call and nothing is missed (the server keeps the last ~10000 events per account). Omit since to start from now; since=0 replays what is retained; a bare integer N returns events with seq > N. EXAMPLES - Wait for hands to post results: watch_events(prefix='task:pr27-review:result:', max_wait_s=25) - Resume: watch_events(prefix='comms:<your-agent-id>:', since='<next_since>') Inside a workspace only events for keys the grant can read are returned. Long-lived clients can use GET /api/v1/events (SSE) instead.

  ConnectorNo auth

• mcp_server_evaluateA

  IA-QA — 130+ QA & Dev Tools for AI AgentsA

  Run a compliance evaluation against a live MCP server over Streamable HTTP, the way a client meets it. Checks: initialize (protocol version, serverInfo, Mcp-Session-Id carried afterwards), notifications/initialized (202), tools/list with pagination, the spec's tool-definition rules, ping, an unknown method (-32601), one tools/call, GET on the endpoint (SSE or 405), and P50/P95 latency over pings. JSON and SSE answers are both read. Only a tool you name in test_tool_name, or one the server annotates readOnlyHint: true, is called — otherwise the call is skipped and not scored. Returns PASS/FIX/BLOCK with a 0-100 score and per-check details; INCONCLUSIVE (score null) when the server requires authorization, since no credentials are sent. A 301/302 on POST caps the verdict at FIX. The call runs from ia-qa.com: private and local addresses are refused, and stdio servers cannot be reached — for those, paste their tools/list answer into mcp_server_health_check. structuredContent is checked for presence, not validated against outputSchema.

  ConnectorNo auth

• ui_keystrokeA

  Local MCPB

  Sends a key combination, e.g. "cmd+shift+5", "return", "cmd+,", "escape". Modifiers: cmd, shift, alt/option, ctrl, fn. The last token is the key. Returns {sent, delivery:"posted_not_confirmed"} — `sent` means the key events were POSTED, NOT that the app acted on them: CGEvent carries no delivery confirmation, and a keystroke's effect is arbitrary so nothing can be read back to prove it. Confirm the effect with ui_get_element / ui_read_tree rather than trusting `sent`. Modifiers are released after the combo, so a following ui_type is not swallowed. unknown_key if the key isn't recognized. Requires Accessibility permission.

  Connector

  Destructive

  OAuth

• record-prospect-outreach-toolA

  CoderbudsA

  Internal Coderbuds staff only. Record that a message was sent to a prospect — after it has actually been sent. **Only call this when you have been told it went out.** Recording a send is what moves a prospect from Sourced to Contacted, and a row that says "contacted" with nothing behind it is worse than one that says nothing: the next session skips it. Sending is not something you can do. If you have written an opener, save it with `save-prospect-draft` and wait to be told it was sent. A draft waiting on the row is folded into the record and cleared, so the same opener cannot go out twice.

  ConnectorOAuth

• get_notification_metricsA

  CourierB

  Delivery funnel for ONE notification template over time: sent, delivered, opened, clicked, errors and undeliverable, per provider and channel, in time buckets. Choosing the window — supply EITHER `lookback` OR `start` and `end` together, NEVER both. Supplying both is rejected. For a relative window like 'the last week', `lookback` alone is the whole answer: do not also pin `start` and `end`. Default is the last 30 days by day. Fine granularities cover shorter windows: HOUR spans at most 7 days and DAY at most 90. How far back a workspace may look also depends on its plan; a request reaching further back is refused with a payment error, which means the plan does not cover that window, NOT that there is no data. A coarser granularity can reach further back than a fine one. Reading the numbers correctly: - The first four counters are NESTED, not separate groups. Every delivered message is also counted in sent, every opened one in delivered, every clicked one in opened. So sent >= delivered >= opened >= clicked always. Report rates (delivered/sent) or the counters themselves. Do NOT add them together — the total is meaningless. And sent minus delivered is NOT a failure count; it is only 'did not reach the delivered stage', for any reason. - errors and undeliverable are counted separately and OVERLAP the funnel: a message that failed on one provider and succeeded on a retry appears in both errors and sent. They are not a remainder and do not complete a total. - Every counter is a count of distinct MESSAGES, not of events. A message that errored three times counts once in errors. - A bucket's `data` array holds one entry per provider and channel. To get a bucket total, add up the entries in that array — that is the only sum that means anything here. Note that rows for Courier's own built-in email sender are excluded, so these entries can add up to less than the workspace's true volume. What the buckets mean: - A message is counted in the bucket it was ENQUEUED in, not when the event happened. An open today of a message sent last Tuesday is counted in last Tuesday's bucket. So a past bucket can still change: yesterday's `opened` may be higher when you ask again tomorrow. - Results are cached for up to an hour and the pipeline adds its own lag, so a message sent minutes ago is expected NOT to appear yet. Never tell a user a just-sent message is missing; say the data has not caught up. - Read the window off the response's `start` and `end`, not off what you asked for. The API widens the window to whole buckets and returns the boundaries it actually used. - Quiet buckets are returned with an empty `data` array, so the series has no gaps. - An unknown template id returns an all-empty series rather than an error, and messages sent without a template never appear here at all. An empty result is not proof a template is unused — check that the id is right before concluding anything from it. - Because of that, a NOT FOUND / 404 error is never about the template id. It means the metrics endpoint itself could not be reached, which is an infrastructure or configuration problem on Courier's side. Say that the metrics service is unreachable and that someone should be told; do NOT tell the user to check or correct their template id, which sends them to fix something that was never wrong.

  ConnectorNo auth

• withdraw_invitationA

  HeyReagent LinkedIn MCPA

  [Ids in: invitationId: sent invitation id, from list_sent_invitations → pendingInvitations[].invitationId. Ids out: none.] Take back ONE connection invitation you sent that is still unanswered, now: its invitationId from list_sent_invitations, or the one send_invitation returned. It is withdrawn on LinkedIn itself and cannot be undone. To take back many at once, withdraw_invitations does that in the background for invitations a campaign sent. Counts against a daily allowance (100 a day).

  Connector

  Destructive

  OAuth

• get_live_scoreA

  Lumify Sports IntelligenceA

  Get a lightweight live score snapshot for an event: status, period, clock, per-participant score and period-by-period scores, and last-updated time. Cheaper and faster than get_event when you only need the score, not participants or venue. Capped at 20 calls/min per key (shared with GET /v1/events/{id}/score and list_events include_scores=true). For live updates prefer the SSE stream. Raises a not-found error if event_id doesn't exist.

  ConnectorAPI key

• get_recent_signalsA

  PredMCPA

  Server-detected events from the last hour: funding outliers (≥3x 7d baseline), whale trades (≥$100k), OI caps reached. Cursor-based — pass next_cursor back as since_id to receive only new events. The polling equivalent of the /sse/signals stream. Pro tool get_signal_history covers 7 days with forward-return outcomes.

  ConnectorNo auth

• wa_set_webhookA

  WhatsMCP: MCP for WhatsAppA

  Register an HTTPS endpoint to receive WhatsApp events as they happen, so you do not have to poll wa_list_messages. By default it delivers inbound messages; pass events to also receive outbound messages (sent from your number), message delivery status (delivered/read/failed), account lifecycle events (connected, disconnected, unlinked, blocked), and call events (completed, missed). Returns a signing secret that is shown ONCE — store it immediately. Calling this again replaces the endpoint and issues a NEW secret.

  ConnectorOAuth

• tascan_cancel_scheduled_smsA

  TaScanB

  Cancel a scheduled text that has not been sent yet (status pending). A row already sending, sent, failed or cancelled is refused (409) — a sent text cannot be recalled.

  Connector

  Destructive

  No auth

• move_eventsA

  PutRootsA

  The signed-in person's move events after an epoch-millisecond timestamp, oldest first — drafted, sent, called, answered, done, skipped. Use it to answer "what changed since we last spoke" without re-reading the whole plan. Capped; more says how many were left out.

  ConnectorNo auth

• telegram_send_mediaA

  Lemma TelepathA

  Send a photo, document, video, audio or voice message to a real person or group from the user's Telegram. Irreversible and immediately visible — confirm the recipient and what is being sent before calling. Give exactly one source: • from_chat_id + from_message_id — forward a file that is already in the archive. Costs no upload and has no size limit, because Telegram already holds the file. Works only for messages the collector saw live; imported history has no file id. • url — a public http(s) link that Telegram fetches itself. In a private chat this is sent as the user. In a group there is no business connection, so it is sent as the bot — say so if that matters.

  Connector

  Destructive

  OAuth

• mcp_crm_txn_email_listA

  MailzzyA

  List transactional (one-to-one) email send logs for the authenticated tenant. Use when the user asks about individual transactional/system emails that were sent (receipts, alerts, password resets), as opposed to bulk campaigns. Supports pagination and a free-text search over the logs. Results come back in the email service's default order (sort=core_default); custom sorting and date/status filters are not available here. Tenant is bound to the session and cannot be changed via tool arguments.

  ConnectorOAuth

• multi_timeframe_analysisA

  TradingMCPB

  Multi-timeframe alignment analysis (Weekly → Daily → 4H → 1H → 15m). Canonical name is exactly `multi_timeframe_analysis` (there is no "get_multi_timeframe_analysis" tool). Use this for cross-timeframe trend alignment on ONE symbol; for a single-timeframe deep dive use `coin_analysis`; for TA + sentiment + news use `combined_analysis`. Example: multi_timeframe_analysis(symbol="SOLUSDT", exchange="BINANCE") Args: symbol: Bare ticker, no exchange prefix — crypto: "BTCUSDT"; stocks: "COMI" (EGX), "THYAO" (BIST), "600519" (SSE), "300251" (SZSE), "2330" (TWSE), "3105" (TPEX), "GDX" (AMEX) exchange: Exchange — crypto: KUCOIN, BINANCE, MEXC; stocks: EGX, BIST, NASDAQ, NYSE, AMEX, NYSEARCA, PCX, SSE, SZSE, TWSE, TPEX, EPA (Euronext Paris), AMS, BRU, LIS, MIL, LSE, SIX, BME, XETRA, FWB, TSX, TSXV, NSE, BSE (India), IDX (Indonesia)

  ConnectorNo auth

• wa_set_webhookA

  whatsmcpA

  Register an HTTPS endpoint to receive WhatsApp events as they happen, so you do not have to poll wa_list_messages. By default it delivers inbound messages; pass events to also receive outbound messages (sent from your number), message delivery status (delivered/read/failed), account lifecycle events (connected, disconnected, unlinked, blocked), and call events (completed, missed). Returns a signing secret that is shown ONCE — store it immediately. Calling this again replaces the endpoint and issues a NEW secret.

  ConnectorOAuth

• upload_media_from_base64A

  PostPlanifyA

  Last resort for small files: upload a file sent as a base64-encoded string. Prefer, in order: upload_attached_file for files the user attached in this chat (ChatGPT); create_upload_url + finish_upload if you can run shell commands (curl); open_upload_box to let the user pick files from their device; upload_media_from_url for public links. The file is stored exactly as received, without compression or resizing. Max size: 7MB. Supports: JPEG, PNG, GIF, WebP, MP4, MOV, PDF. Returns a media ID that can be attached to a post.

  ConnectorOAuth