"Using mcp-proxy to bridge a remote SSE server to a stdio server" matching MCP tools:

• setup_local_cryptoA

  seekrit — secrets for agentsA

  Get the exact commands for running the local crypto plane (the `@seekrit/mcp` npm server, the `@seekrit/cli` CLI, seekrit-run, seekrit-proxy), including a copy-paste .mcp.json that reuses this session's credential. Takes no arguments and returns prose plus config. Call this the moment you need to SET or READ a secret value — no tool on this server will ever return one. Use local_tool_for instead when you want the single command for one named operation.

  ConnectorNo auth

• whatsapp_config_setA

  WhatsAppC

  Change an editable-after-connect setting on a connected number WITHOUT re-pairing. Today the only field is `proxy_url` — the SOCKS5/HTTPS proxy WhatsApp connects through (recommended to avoid IP bans). Owner/admin or the connection owner. - `account`: which number (id/wa_jid, phone, or label; omit if only one is connected). - `values`: e.g. { "proxy_url": "socks5://user:pass@host:port" }. An empty string CLEARS the field (e.g. { "proxy_url": "" } connects with no proxy); omit the key to keep the current value. The new value applies on the next (re)connection; the live session cache is invalidated so the next tool call uses it.

  ConnectorNo auth

• update_password_policyA

  The BridgeA

  Set the session token lifetimes on the Bridge app: accessTokenTTL and refreshTokenTTL, both in SECONDS. Only the fields you pass are changed. IMPORTANT — despite the name (kept for parity with `bridge auth password-policy`), this sets token TTLs and NOTHING about passwords: Bridge exposes no password-complexity, rotation or reuse policy on the management API, so if the user asked for password rules, say so instead of calling this. The access token TTL controls how often a client silently refreshes (short is safer, e.g. 900 = 15 minutes); the refresh token TTL controls how long a user stays logged in without re-authenticating (e.g. 2592000 = 30 days). Read the current values with get_auth_config. Before writing app code that consumes this, call get_integration_guide with topic=auth and the framework the app uses.

  ConnectorOAuth

• network_listenersA

  ReMCPB

  Use this when the user asks to inspect listening ports on a paired computer to diagnose local services, unexpected exposure or port conflicts. Reads the OS TCP listener inventory on Windows and macOS, and TCP/UDP listeners on Linux; process details depend on OS permissions. It does not connect to ports, scan remote hosts or change firewall rules.

  ConnectorOAuth

• createProxyResourceA

  2extractA

  Create a new residential or mobile proxy resource on the account. Check getAccountBalance and require can_create_proxy to be true; usage is billed according to the selected plan (tariff_id from listProxyPlans). The name must be unique on the account and cannot be changed later. Limits can be set here or later with setProxyLimits. Returns the complete new proxy, including its password. Use buildConnectionString to get a connection string. Response fields: docs://proxies/createProxyResource.

  ConnectorNo auth

• list_variablesA

  mcpA

  List account variable NAMES (values are write-only — they are injected into proxy calls and container apps, never read back).

  ConnectorNo auth

• 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

• wait_for_updateA

  cnvs.appA

  Long-poll: blocks until the next edit lands on this board, then returns. WHEN TO CALL THIS: if your MCP client does NOT surface `notifications/resources/updated` events from `resources/subscribe` back to the model (most chat clients do not — they receive the SSE event but don't inject it into your context), this tool is how you 'wait for the human' inside a single turn. Typical flow: you draw / write what you were asked to, then instead of ending your turn you call `wait_for_update(board_id)`. When the human adds, moves, or erases something, the call returns and you refresh with `get_preview` / `get_board` and continue the collaboration. Great for turn-based interactions (games like tic-tac-toe, brainstorming where you respond to each sticky the user drops, sketch-and-feedback loops, etc.). If your client DOES deliver resource notifications natively, prefer `resources/subscribe` — it's cheaper and has no timeout ceiling. BEHAVIOUR: resolves ~3 s after the edit burst settles (same debounce as the push notifications — this is intentional so drags and long strokes collapse into one wake-up). Returns `{ updated: true, timedOut: false }` on a real edit, or `{ updated: false, timedOut: true }` if nothing happened within `timeout_ms`. On timeout, just call it again to keep waiting; chaining calls is cheap. `timeout_ms` is clamped to [1000, 55000]; default 25000 (leaves headroom under typical 60 s proxy timeouts).

  ConnectorNo auth

• pingA

  Nordic Financial MCPA

  Connectivity check that confirms the Nordic MCP server process is responding. Use this at the start of a session to verify the server is reachable before making other calls. Do not use as a proxy for database health — the server can respond while the Qdrant vector database is temporarily unavailable. To confirm data availability, call search_filings directly. Returns: A greeting string: "Hello {name}! Nordic MCP server is running."

  ConnectorNo auth

• render_resume_pdfA

  ResumeMDA

  Render a Markdown resume to a finished PDF using a ResumeMD template (default: classic — see list_resume_templates for all 32 ids). Returns JSON with a base64-encoded PDF and a suggested filename; decode the base64 to give the user the file. The PDF is generated in memory and never stored. For interactive editing, template switching, and color choices, send the user to resumemd.pro/editor instead.

  ConnectorNo auth

• resolve_factorA

  apiA

  Find the best emission-factor key(s) for a plain-language description — the hardest step is picking the right key out of ~16,000. Returns ranked matches, each carrying the key, value, unit and a confidence score; feed the chosen key to a calculate_* tool or lookup_factor. Prefer this over guessing a key. PUT THE COUNTRY IN THE DESCRIPTION. Geography is read from the description text itself, not from a separate field — "diesel per litre" and "diesel per litre France" resolve differently, and omitting the country will quietly return a factor from somewhere else marked "geo_match":"proxy". ACT ON THE LABEL. Every candidate carries label: "accept" or "review", plus "why". "accept" means confidence >= 0.85 and no demotion applied — right about nine times in ten. "review" means the answer may be usable but something is off (low confidence, only one term matched, a proxy country, or a gate demoted it); confirm it before adopting the number rather than using it silently. Roughly half of CORRECT answers are also flagged "review" — that is the intended trade, so treat "review" as "check this", not "discard this". A MISS MAY EXPLAIN ITSELF. When nothing matches, or the only matches are from the wrong country, the response may carry an "absence" object saying WHY. classification "structural" means no publisher issues this anywhere — STOP, do not retry with reworded queries and do not substitute a different country without saying so. "not_yet_sourced" means a publisher exists and we have not ingested it (the publisher is named). "refused" means we found the data and declined it, with the reason. "coupled" means this reads empty only because a related family is empty. Use explain_absence to ask the same question directly.

  ConnectorNo auth

• register_serverA

  PayGate MCPA

  Start charging for an MCP server the user owns. Use when they want to monetize, sell, charge for, get paid for, put a price on, or make money from a server, API or tool. Buyers pay their wallet DIRECTLY on-chain — PayGate never holds the money, so there is no payout to wait for, no balance to withdraw and no commission taken. Their server is never modified and needs no payment code. Tools are imported automatically, so it must be publicly reachable over HTTPS and answer tools/list. Returns a proxy URL and a secret api_key shown only once; save it, every other seller tool needs it.

  ConnectorNo auth

• register_serverA

  PayGate MCP — Monetization Gateway for AI AgentsA

  Start charging for an MCP server the user owns. Use when they want to monetize, sell, charge for, get paid for, put a price on, or make money from a server, API or tool. Buyers pay their wallet DIRECTLY on-chain — PayGate never holds the money, so there is no payout to wait for, no balance to withdraw and no commission taken. Their server is never modified and needs no payment code. Tools are imported automatically, so it must be publicly reachable over HTTPS and answer tools/list. Returns a proxy URL and a secret api_key shown only once; save it, every other seller tool needs it.

  ConnectorNo auth

• correct_interestA

  mcpA

  Record the user's correction to an inferred interest, using a key from get_interests. Corrections are sticky — they survive every future recompute. Use `confirm` when they agree, `rename` for their own wording, `hide` to stop using an interest while keeping its history, `boost` when they want it weighted higher. `forget` is different and IRREVERSIBLE: it erases the underlying history so the topic cannot re-form — only use it when the user clearly asks to delete, and say what it means first.

  ConnectorNo auth

• springroll.deployA

  SpringRollA

  Registers the project if it is new, attaches whatever source you give it, and deploys it using the application's Deployment workflow. Direct applications go to Production; Staged applications go to Development. Returns the live URL, or a deployment id to poll if the build is still running. **You do not decide whether this project needs git.** Send what you have and SpringRoll works it out: • a pushed git remote → pass `repositoryUrl` (and `ref` if not the default branch) • no remote, or uncommitted work → pass `archive`, a base64 tar+gzip of the source: tar --exclude=node_modules --exclude=.next --exclude=.git --exclude='.env*' \ -czf - . | base64 -w0 • both → SpringRoll builds from git, and falls back to your files if the ref cannot be resolved (an unpushed branch, typically) • neither, on an app that already exists → redeploys its current source Upload SOURCE, not build output: SpringRoll runs the build. node_modules, .next, dist, build, out, coverage and .log files are dropped automatically and reported. Every .env file and .git/ is REFUSED outright, naming the offending path: configuration belongs in SpringRoll, not in the bundle. Upload limits are about 3 MB compressed on the wire (a platform request-body cap, not a preference), 20 MB expanded, 2000 files, 512 KB per file; a project past them should pass `repositoryUrl` instead, which SpringRoll clones directly with no size limit. Sending the same files twice is free, because bundles are addressed by content. Direct to Production skips workflow approvals but keeps production safety checks. Staged applications continue to use explicit promotion and approvals.

  ConnectorNo auth

• search_jobsA

  Roleset — job postings indexA

  Search the index of open job postings. Use for a one-off question about the job market: who is hiring for a role, what is open in a city or country, which companies have remote positions. Returns a page of job records plus a `meta.next_cursor` to continue; each record has title, company, structured locations, remote flag, employment type, salary when the board publishes one, and an apply URL. Descriptions are omitted unless `include_description` is set, because they are large. To find what has *changed* since you last looked, use job_changes instead — do not poll this tool in a loop.

  ConnectorNo auth

• upload_fileA

  NexDoc DesignA

  stdio MCP only: read a local path, SHA-256 the bytes, upload to NexDoc (or reuse an existing file for this user when content matches), and return a ready file_id. Use this instead of asset_files for large photos. Then pass file_ids to create_design or update_design. Remote/OAuth MCP cannot read the client's disk — use request_file_upload (with optional content_sha256) and PUT instead.

  ConnectorOAuth

• create_designA

  NexDoc DesignA

  Create a job (or reuse job_id) and start a generative run. Omitting job_id ALWAYS creates a NEW job — call at most ONCE per user request. If you already have a job_id (including from a prior create_design error), pass it or use update_design; never call create_design again without job_id for the same request. The API rejects a second run on a job while one is still queued or running (409) — if a run fails or stalls, report it and ask the user before cancelling or re-running. Always tell the user job_id and run_id as soon as this returns. If the result includes concurrency_notice, show that reminder (pay-as-you-go accounts run one design at a time). Do not set wait:true. If the user asked to be emailed (including in the original request), set notify_email:true here immediately — do not wait until after wait_for_run. After create, call wait_for_run ONCE (default ~45s). If still_running and they have not already asked for email, stop polling, show the IDs, and offer notify_run_email. Photos/logos: prefer request_file_upload (or upload_file on stdio) then pass file_ids — never compress or generate a replacement. asset_paths is stdio-only; asset_files base64 is a last resort for tiny files. After completion, return viewer_url and offer export (pdf/html/png) — do not publish unless the user asks.

  Connector

  Destructive

  OAuth

• null_void_descriptorA

  Robyn — Gasless Cross-Chain for AI AgentsB

  Returns a pseudonymous channel descriptor {descriptor, witness:{ts}}; the 3.3 KB ML-DSA signature and the handle-ownership proof come as separate parts (part=sig | part=proof) because they cannot share one 8 KiB lane reply. Verify all three locally (SDK voidVerifyDescriptor) before following. Private-lane-only (a direct lookup would tell the gateway which channel your IP wants): use the stdio door.

  ConnectorNo auth

• export_ticket_to_providerA

  Meta CouncilB

  Export the exact previewed owned ticket to Jira or Linear, using expected_export_hash from preview_ticket_export and the same destination. Requires explicit integrations:write, tickets:write, and independent human approval of the complete preview. Persists the operation before possible remote writes. After an uncertain response, inspect list_ticket_provider_effects and reconcile the original intent; never blindly export again. Remote confirmation is observed, not atomic protection against concurrent remote writers.

  ConnectorNo auth

• draft_responseA

  Outreach DeskA

  Use this to draft a reply to a scored pitch: an interested reply, a request for salary and remote details, or a polite decline. It needs an evaluation_id from score_message or get_scoreboard; evaluations expire after 30 days. Errors: unknown_evaluation means score the pitch again with score_message and use the new evaluation_id; no_desk means call set_criteria first. Decision defaults to the recommended action. For a decline, ask the user whether to include the feedback card. Returns subject and body as a draft only; it never sends anything, and the user sends the reply themselves. The desk is the signed-in user's, so send no desk_key.

  ConnectorNo auth