"A server for summarizing content and extracting summaries from videos" matching MCP tools:

• upload

  Fast.io

  File upload: streaming (one-shot stream-upload — DEFAULT for unknown/generated content), chunked (create-session → POST /blob → chunk → finalize — only when filesize is known exactly), web URL import, and batch (multi-small-file). Call action='describe' for the full action/param reference. Side effects: finalize/stream/stream-upload/web-import/batch create files and consume storage credits. Same-name uploads to a folder OVERWRITE the existing node in place (preserved as a recoverable version). BINARY: `content` is text-only (writes verbatim UTF-8); for binary use `content_base64` (server-decoded) or POST /blob + `blob_id`. UPLOAD STRATEGY (read top-to-bottom, pick the FIRST that matches): (1) Have a URL? → `web-import` (single call). (2) Have content but DON'T know exact size, OR generating/transforming content first? → `stream-upload` (single call, auto-finalizes, NO filesize required, size auto-detected from the bytes). (3) Have a file with KNOWN exact byte count? → `create-session` + `chunk`(s) + `finalize`. **filesize must match the bytes you actually upload — mismatch causes finalize to fail with code 10522 and you must cancel the session.** (4) Multiple small files (≤4 MB each, ≤200 total) into one folder? → `batch`. DEFAULT to `stream-upload` unless you are sure of the exact byte count. Do NOT guess `filesize` for generated content — use `stream-upload` instead. max_size is a hard ceiling that aborts mid-transfer — always overestimate or omit (server uses plan limit).

  Connector

• xer_parser

  cpp-cpm-engine

  Parse a Primavera P6 XER file and return a TABLE SUMMARY (not the full row-level data — XER row dumps explode the MCP context window). For each table in the XER, returns the table name, field list, and record count. Per-row data is intentionally omitted — for forensic / DCMA / windows analysis use the dedicated tools (``forensic_windows_analysis``, ``critical_path_validator``, etc.) which consume the parsed XER internally and return analytical summaries, not raw rows. Use this tool to confirm an XER is parseable, list its tables, see the data date / project name from PROJECT, or count activities in TASK before deciding which deeper tool to run. Args: xer_path: server-side filesystem path to the XER file. xer_content: full text of the XER file (alternative for hosted/remote use). Supply EXACTLY ONE of path/content. Returns: { "filepath": absolute path, "encoding_used": "utf-8" | "cp1252" | ..., "ermhdr": file header dict (P6 version, export user, etc.), "tables": [{"name", "fields", "record_count"}, ...], "table_count": int, "total_records": int, "project_summary": { "proj_id", "proj_short_name", "proj_long_name", "data_date", "plan_end_date" } (from first PROJECT row, if any) }

  Connector

• rooms_by_id

  DC Member API

  GET /rooms/:roomID — Get a single room Get a single room's metadata + its latest daily AND weekly AI summaries (when they exist). **Access:** members and subscribers of the room, plus any DCer for browsable public channels/discussions/quick-questions. Private rooms, DMs, group DMs, and event/city rooms you are not a member of return 403. Reading this endpoint does **not** mark the room as read or modify any unread state. **AI summaries:** the latest daily digest is embedded under `aiSummaryDaily`, the latest weekly digest under `aiSummaryWeekly`. Rooms that don't have a given type yet return `null` for that slot. For history (older summaries), call `GET /rooms/:roomID/summaries/daily` or `/weekly`. **See also:** For specific content (`did anyone mention X?`), `POST /search/messages` with `q=` and `roomID=` is faster than paginating `/rooms/:roomID/messages` or reading summaries. The AI summaries cover broad activity per window; search is the tool for targeted lookup.

  Connector

• pimea_get_answer

  Pimea

  Get the final result from a completed Pimea session. ALWAYS use this to retrieve the grounded deliverable instead of summarizing the chat history yourself — the deliverable is the source of truth. Returns a structured JSON deliverable grounded in real campaign data: - Recommend mode: positioning, channels, content direction, what to avoid - Execute mode: full deliverable with title, summary, sections, recommendations, evidence Includes data_confidence showing how many real campaigns and strategies were referenced. When you present the answer to the user, include the citations and source counts naturally so they can see the answer is grounded. Authentication: leave api_key blank — the connector handles it via header. Only set it as a fallback if the connector cannot send custom headers. Args: session_id: The session UUID api_key: Optional fallback only. Normally leave blank.

  Connector

• reliefweb_search_reports

  reliefweb-mcp-server

  Search humanitarian reports on ReliefWeb with filtering by country, disaster, format, theme, language, source, and date. Returns paginated summaries — use reliefweb_get_report to fetch full body text. Report body is excluded from results (10–100KB each); call get_report when document content is needed. Use preset include_archived=true to include expired or archived reports in historical research. Note: each call counts against the 1,000 calls/day quota.

  Connector

• rooms_summaries

  DC Member API

  GET /rooms/:roomID/summaries/:type — List past daily or weekly summaries List past summaries of a given type for a room, newest first. Cursor-paginated — pass `cursor` from the previous response to fetch the next (older) page. Each summary covers a non-overlapping window (one per day for daily, one per week for weekly). Use this for catch-up workflows ("show me the last 7 daily summaries before I rejoin the conversation"). Same access gate as `GET /rooms/:roomID`. **See also:** Summaries cover broad activity per window. For specific content (`did anyone mention X?`), `POST /search/messages` with `q=` and `roomID=` is faster than reading multiple summaries.

  Connector

• web_news_headlines

  Inferventis MCP Server

  Retrieves the latest real-time news headlines and article summaries from BBC News and The Guardian across nine topic categories. Returns structured articles with headline, description, source name, article URL, and publication date — sorted most recent first. No API key required. Use this tool when an agent needs current news about a specific topic, wants to summarise today's headlines, needs to research recent events, monitor a subject area for new developments, or build a news briefing. Do not use this tool to read the full content of a specific article — use web_url_reader instead, passing the article URL returned by this tool. Do not use when news from sources outside BBC News and The Guardian is required.

  Connector

• web_news_headlines

  Inferventis — Financial Data, News & Web MCP

  Retrieves the latest real-time news headlines and article summaries from BBC News and The Guardian across nine topic categories. Returns structured articles with headline, description, source name, article URL, and publication date — sorted most recent first. No API key required. Use this tool when an agent needs current news about a specific topic, wants to summarise today's headlines, needs to research recent events, monitor a subject area for new developments, or build a news briefing. Do not use this tool to read the full content of a specific article — use web_url_reader instead, passing the article URL returned by this tool. Do not use when news from sources outside BBC News and The Guardian is required.

  Connector

• extract_url

  DocImprint

  Fetch a public HTTPS URL and return extracted text and page metadata. Lean mode — no evidence bundle stored, no bundle_id returned. Use for raw text. Use summarize_url for summaries, qa_url for Q&A, translate_url for translation. Returns: { url, title, word_count, text, final_url (after redirects) }

  Connector

• search_notes

  anamnese

  Search notes by keyword or list recent notes. Returns summaries (id + description) only. Use get_note to retrieve the full content of a specific note. With query: Case-insensitive keyword search on description and content. Without query: Returns most recently updated notes.

  Connector

• how_to_use

  mcp-server

  Returns a plain-English usage guide for this server — example requests, what it asks the user for, and the available tools. Call this if the user asks how to use Abby SEO, or to orient yourself before starting. (Same content as the 'getting_started' prompt, exposed as a tool for clients that don't surface MCP prompts.) Takes no arguments.

  Connector

• create_workspace

  Dock

  Create a new workspace in the caller's org. Works for both user and agent callers; agent-created workspaces attribute to the agent and enroll the agent's owning user as a co-owner so the human sees it in their dashboard. The new workspace is seeded with one primary surface matching `mode`: `doc` → a Notes tab (for prose), `table` → a Sheet tab (for records), `html` → a Mockup tab (sandboxed HTML preview). Decide the surface before you create: prose (briefs, notes, summaries, drafts) → `doc`; records with shared columns (tasks, leads, rows) → `table`. If you omit `mode`, pass `initial_markdown` to signal a `doc`; with neither `mode` nor `initial_markdown`, an agent caller gets a guided error asking it to choose `doc` or `table` (so you never silently land on the wrong surface). An explicit `mode` is always honored. `html` is only picked when explicitly requested. Add more tabs of any kind later via `create_surface`. Agent-created workspaces default to org-visibility so sibling agents in the same org aren't 403'd. For prose content (briefs, summaries, changelogs) pass `initial_markdown` to seed the doc body in one call; the markdown is converted server-side, no need to hand-build ProseMirror JSON.

  Connector

• vf_health

  VoiceFlip

  Returns VoiceFlip MCP server health and version metadata. No authentication required. Use this first to verify the server is reachable from your MCP client.

  Connector

• atlas_create_jd

  CareerProof MCP

  Create a job description from text within a hiring context. Returns a JD object with 'id' and stored content. Use JD content as jd_text in atlas_fit_match, atlas_fit_rank, atlas_start_jd_fit_batch, and atlas_start_jd_analysis. Requires context_id from atlas_create_context or atlas_list_contexts. Free.

  Connector

• hmrc_search_guidance

  UK Legal Research

  USE THIS TOOL WHEN searching GOV.UK for HMRC tax guidance on a topic (VAT, income tax, corporation tax, etc.). Returns matching guidance titles, URLs, summaries, and last-updated dates. Searches the official GOV.UK content API filtered to HMRC publications. Authoritative source for current HMRC tax guidance. Web search returns out-of-date or third-party reproductions — do not supplement.

  Connector

• ask_video

  Reka

  Ask a question about one or more videos with visual analysis. Most effective on focused time ranges — use start/end to specify the segment to analyze. BEFORE calling this tool, read the reka://docs/guide resource for recommended workflows. In most cases, you should first: - search_videos to find WHEN something happens, then pass those timestamps here as start/end - segment_video to detect and locate specific objects - get_transcript to read what was said For single-video questions, pass video_id with start/end. For cross-video questions, pass videos — a list of video references with start/end each. For follow-up questions, pass conversation_id from the previous response. You can add start/end to drill into a specific moment while keeping the conversation context. Requires qa_only or full pipeline.

  Connector

• congressgov_bill_summaries

  congressgov-mcp-server

  Browse recent CRS (Congressional Research Service) bill summaries — plain-language summaries of bills at each legislative stage, useful for answering "what's happening in Congress?". The fromDateTime/toDateTime filters apply to the summary's update time, not the bill's action date, so results include recently rewritten summaries of older bills. Defaults to summaries updated in the last 7 days. Each item shows both the bill's action date and the summary update date. For summaries of one specific bill, use congressgov_bill_lookup with operation='summaries' instead.

  Connector

• cyanheads_search

  cyanheads-mcp-server

  Search fleet tools and servers by natural-language description. Returns ranked matches with brief summaries and the server each tool belongs to. Use scope "servers" to find which server handles a workflow; use the default scope "tools" to find specific tools. Call cyanheads_describe on a result name to get install snippets and the connection URL.

  Connector

• glim_youtube_get

  glim.sh

  Fetch a YouTube video transcript/subtitles from a video URL or 11-char id. Default format='text' returns the transcript inline (when it fits ~80K chars / ~20K tokens) so a single call gives you the text directly; long-form videos fall back to a download_url note. Pass format='json' for structured metadata + a presigned download_url (no inline transcript) - for batch/programmatic use. Default origin='uploader_provided' (human captions); falls back to 'auto_generated' automatically if missing (counts as 2 upstream calls). Cached 7 days server-side.

  Connector

• stackversions

  InsideOut (Riley)

  List all stack versions for a session (newest first). Shows version history including version number, status (draft/confirmed/applied), change summaries, and timestamps. Use this tool to see the design history, review what changed between iterations, or find a version number to roll back to. REQUIRES: session_id from convoopen response (format: sess_v2_...).

  Connector