"How to use remote URLs with SSE without local files" matching MCP tools:

• read_code

  Zephex

  Extracts code surgically via tree-sitter AST — not repo-wide search. Eight modes; envelope: mode, focus, summary, data, hint, related_modes, next_calls, meta (meta.tokens_returned, meta.credits, meta.charges_usage). Hosted: 5 credits per success; failures free. Cheapest path: mode file or outline with files[] you already have — ~300–2000 tokens vs full-file Read (data.tokens_saved_vs_full_files). Expensive: mode symbol without find_code first on large repos (may scan many files). Free alternative: editor Read on files under ~50 lines. symbol: fuzzy match by name; symbol_id direct lookup; detail_level signature|body|context; targets[] batch (max 8). file: batch 1–20 paths, paginate offset_line. outline: TOC + plain-English overview before 300+ line files. scan/smell: keyword or bug patterns across known files[] only. callers|blast_radius|dead_code: local SQLite call-graph (index builds after first symbol call on that path) — not on hosted without disk; use find_code for remote usage search. Call when: symbol or files[] known (from find_code or explain_architecture next_calls). Do NOT when: location unknown (find_code); stack (get_project_context); wiring map (explain_architecture); repo-wide grep (find_code). Pass path (absolute dir) or inline_files. compact:true saves tokens; session_id dedupes across turns. After: summary + next_calls before paging. Read-only.

  Connector

• find_examples

  Senzing

  Find working SOURCE CODE examples from 37 indexed Senzing GitHub repositories. REQUIRED: either `query` (string, for search) or `repo` with `file_path` or `list_files=true` — the call WILL FAIL without one. Three modes: (1) Search: pass `query` to find examples across all repos, (2) File listing: pass `repo` + `list_files=true`, (3) File retrieval: pass `repo` + `file_path`. Indexes source code (.py, .java, .cs, .rs) and READMEs — NOT build/data files. For sample data, use get_sample_data. Covers Python, Java, C#, Rust SDK patterns: initialization, ingestion, search, redo, configuration, message queues, REST APIs. Use max_lines to limit large files. Returns GitHub raw URLs for file retrieval.

  Connector

• recipe_delete

  local-mcp

  Use this when the user wants to remove one of THEIR saved recipes/skills (the manifests under ~/.local/share/local-mcp/recipes). Destructive with a preview gate: the first call (without confirm) shows what would be deleted; call again with confirm=true to actually delete. Bundled starter recipes can't be deleted. To modify a recipe instead, recipe_save with the same name overwrites it (upsert).

  Connector

• word_create

  local-mcp

  Creates a new Word (.docx) document at `path` with the given text content (and an optional title rendered as the heading). Requires confirm=true — called without it, returns a preview of what will be written instead of creating the file. The path must be somewhere Local MCP can write; Desktop/Documents/Downloads may need a one-time Files-and-Folders grant (System Settings → Privacy & Security → Files and Folders). Returns {created, path}. For a OneDrive or Google Drive path use onedrive_write_file / gdrive_write_file; to append to an existing doc use word_append, to read one word_read.

  Connector

• send_message

  Fast MCP Telegram

  Send text and optional file attachments to a Telegram chat. Supports reply-to (including forum topics and channel discussion groups), parse_mode: classic markdown/html/auto (entities) or rich (Rich Message document; dialect auto-detected). parse_mode=rich cannot be combined with files. File attachments as http(s) URLs, local paths, or data: URIs. When files are provided, the message text becomes a caption. For channel posts with reply_to_id, automatically posts in the linked discussion group. Success: dict with message_id, date, chat, text, status='sent', and sender info (rich messages also set rich=true and rich_format). Error: dict with ok=false and error string. Use send_message to create new messages; use edit_message to modify existing ones. Use send_message_to_phone when targeting a phone number instead of a chat_id. Full documentation: https://github.com/alexeyleshchenko/fast-mcp-telegram/blob/main/docs/Tools-Reference.md

  Connector

• send_message

  fast-mcp-telegram

  Send text and optional file attachments to a Telegram chat. Supports reply-to (including forum topics and channel discussion groups), parse_mode: classic markdown/html/auto (entities) or rich (Rich Message document; dialect auto-detected). parse_mode=rich cannot be combined with files. File attachments as http(s) URLs, local paths, or data: URIs. When files are provided, the message text becomes a caption. For channel posts with reply_to_id, automatically posts in the linked discussion group. Success: dict with message_id, date, chat, text, status='sent', and sender info (rich messages also set rich=true and rich_format). Error: dict with ok=false and error string. Use send_message to create new messages; use edit_message to modify existing ones. Use send_message_to_phone when targeting a phone number instead of a chat_id. Full documentation: https://github.com/alexeyleshchenko/fast-mcp-telegram/blob/main/docs/Tools-Reference.md

  Connector

• picsart_remove_bg

  Picsart GenAI

  Removes the background from an image, returning a transparent cutout of the foreground subject. Auto-picks the newest enabled Picsart remove-bg model unless overridden via the `model` param — no need to call `picsart_list_models` first. Use this when the user asks to "remove the background", "cut out the subject", or "make the background transparent". Do NOT use this to replace the background with a new scene (use `picsart_change_bg`), upscale or sharpen the result (use `picsart_enhance`), convert raster to SVG (use `picsart_vectorize`), or generate a new image from scratch (use `picsart_generate`). Required input: `image` — a publicly-accessible URL. Local files are not supported; if you only have a local file, first make it available as a public or app-authorized URL. Optional: `model` to pin a specific remove-bg model, `outputFormat` (e.g. "png"). Example: `{ image: "https://example.com/portrait.jpg" }`. Returns `{ assets, id, model, created_at, summary, why_relevant, url, results: [{ url, metadata? }], drive? }` as a single JSON text block plus matching structuredContent (no `resource_link` blocks — the widget is the single source of visual truth, so result URLs are not duplicated as separate content blocks). `id` is the SDK's generation handle; `metadata` may include model-specific tags. Spends credits. Requires Authorization: Bearer <picsart_token>.

  Connector

• get_site_info

  Bogeyland

  Returns basic information about this neighborhood directory: name, locale, domain, description, canonical URLs for key sections, plus the current LOCAL TIME and CURRENT WEATHER at the neighborhood (temperature, condition). Use this for any "what time is it there" or "what's the weather like" context.

  Connector

• search

  JobYap Job Search

  Search JobYap job postings by natural-language query. Matches job titles, falling back to significant keywords when the full phrase finds little. Returns result ids, titles and citable URLs for use with fetch. For structured filtering (location, company, remote, freshness) prefer search_jobs.

  Connector

• axint.agent.claim

  Axint

  Claim files before an agent edits them so other agents do not patch the same SwiftUI/App files concurrently. Claims are local, short-lived, and stored in .axint/coordination/claims.json. Use: use before editing shared files in parallel-agent work; release claims when done. Inputs: agentId and files identify the claim; ttlMinutes bounds ownership and force overrides stale claims. Effects: writes local coordination claims under .axint/coordination; no network.

  Connector

• axint.agent.release

  Axint

  Release active local Axint file claims for this agent after finishing or abandoning a task. This keeps parallel agents and Xcode from blocking each other on stale claims. Use: use after finishing or abandoning claimed files; use agent.claim before edits and agent.advice for next steps. Inputs: agentId releases only its matching claims unless files narrow the release set. Effects: updates local coordination claims under .axint/coordination; no network.

  Connector

• fvs_download_final_video

  Future Video Studio

  Download a completed Future Video Studio final render URL to a local file. Use this only after fvs_get_render_status or fvs_get_paid_render_status returns a final_video_url for a completed render. The tool performs an unauthenticated HTTPS GET to that signed URL and writes the response bytes to output_path on the MCP server's local filesystem. It does not call the FVS Agent API, spend wallet credits, require FVS_AGENT_API_KEY, cancel jobs, or modify remote render state. Side effects and constraints: output_path is a local filesystem path for the MCP server process, parent directories are created, existing files are not replaced unless overwrite is true, and large videos may take minutes to download. The request timeout is 600 seconds. Use a fresh status check to refresh expired signed URLs, and do not pass arbitrary or untrusted URLs.

  Connector

• stream_task

  TunnelMind Data API

  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.

  Connector

• deploy_site

  vibedeploy

  Publish a website to a live URL. Deploy a static site or single-page app you built (with AI or by hand) to your platform subdomain (e.g. {name}.vibedeploy.be or {name}.vibedeploy.eu) with automatic SSL, and optionally a custom domain. The fastest way to get a localhost project or an AI-generated site online. DESTRUCTIVE on existing sites: replaces every file on the named site with the supplied set. Files not in this call are deleted. For a new site, creates and provisions it. For an existing site, requires `confirm: "I-want-to-replace-all-files"` to proceed; without confirm the call is rejected before anything is touched. Use update_site (default mode:'patch') if you want to add or change individual files without removing the rest. Use dryRun:true to preview the diff. LARGE FILES: don't split a big text file across a placeholder deploy + chunked follow-ups — a 100-250 KB HTML/CSS/JS file fits in THIS call when sent with encoding:'gzip+base64' (gzip locally, base64 the result; text compresses 3-5×). The site is published at your platform subdomain (e.g. {name}.vibedeploy.be or {name}.vibedeploy.eu). After deploy, call add_custom_domain to also serve at a user-owned hostname.

  Connector

• scaffold_service

  @imqueue

  READ-ONLY: returns generated source code as text and writes nothing to disk, creates no project and runs no command. Generates an idiomatic @imqueue/rpc service (an IMQService subclass with @expose()d, JSDoc-typed methods) plus a bootstrap that starts it. Provide the methods you want, or omit them for a starter template. Any non-primitive parameter or return type also gets a types.ts with the required @classType()/@property() declarations — without those the generated client types it `any`, which compiles. Use create_service (local install only) if you want files actually written.

  Connector

• bucket_update_publication_access

  Revdoku

  Change an already-published website's access settings WITHOUT republishing its files or URL. Use this to switch a live site between public, password, and Require Email, or rotate the password. Same-storage-class changes (e.g. password <-> Require Email, rotate password) are instant settings updates; switching public <-> protected re-keys the files and may take longer but keeps the site live. To publish a NEW VERSION of the files, use bucket_publish / bucket_publish_password_protected instead. Never put passwords in URLs. An access-mode change fails with BUCKET_VISIBILITY_CHANGE_LOCKED if the bucket's visibility is locked (unlocking is web-UI-only — ask the user); rotating the password or other same-access-mode settings stay allowed while locked.

  Connector

• save_to_drive

  Hermoso

  Save a Hermoso render — or ANY file — into the user’s connected Google Drive. Pass a Hermoso render URL as url (or urls[] for several); for a local/external file, call upload_file first and pass the url it returns. Optional folder (created if new) + name. Returns the Drive file(s) with a webViewLink. Needs Google Drive connected (Settings ▸ Connectors ▸ Google Drive — one connection covers Drive, Sheets and Docs). NOTE: Hermoso uses the drive.file scope, so it reaches ONLY the files it created plus any the user explicitly handed over with the Google file picker in the app — never their whole Drive.

  Connector

• publish_site

  mcp

  Deploy files to a live URL. No slug → create a NEW site (works without auth; anonymous sites expire in 24h — always show the user the claimUrl). With slug → UPDATE that site (complete snapshot: send ALL files). A Dockerfile in the files makes it a server-side app (auth required; listen on process.env.PORT; persist under /data; poll app_status). Total payload ≤ 8 MB — for bigger sites use the dataecho skill scripts.

  Connector

• discovery_upload

  Disco

  Upload a dataset file and return a file reference for use with discovery_analyze. Call this before discovery_analyze. Pass the returned result directly to discovery_analyze as the file_ref argument. Provide exactly one of: file_url, file_path, or file_content. Args: file_url: A publicly accessible http/https URL. The server downloads it directly. Best option for remote datasets. file_path: Absolute path to a local file. Only works when running the MCP server locally (not the hosted version). Streams the file directly — no size limit. file_content: File contents, base64-encoded. For small files when a URL or path isn't available. Limited by the model's context window. file_name: Filename with extension (e.g. "data.csv"), for format detection. Only used with file_content. Default: "data.csv". api_key: Disco API key (disco_...). Optional if DISCOVERY_API_KEY env var is set.

  Connector

• firecrawl_parse

  firecrawl-mcp

  Parse one supported document into markdown, HTML, links, summary, targeted answers, or JSON matching a schema. Supported inputs include common HTML, PDF, Word, RTF, OpenDocument, and spreadsheet files; PDF parsing can be bounded with `pdfOptions.maxPages`. Local MCP reads `filePath` from the server filesystem. Hosted MCP uses two calls: first provide `filePath` to receive upload instructions, upload locally, then call again with the returned `uploadRef`; do not send both fields together. Remote web URLs belong in `firecrawl_scrape`. Set `redactPII` to request redaction of personally identifiable information in the returned content. `zeroDataRetention` requires an eligible authenticated account; omit it for anonymous keyless use. Returns upload instructions for hosted phase one or parsed document content for the final call.

  Connector