"MCP servers for reading and parsing PDF, Word, and PowerPoint documents" matching MCP tools:

• ateam_redeploy

  ateam-mcp

  Re-deploy skills WITHOUT changing any definitions. ⚠️ HEAVY OPERATION: regenerates MCP servers (Python code) for every skill, pushes each to A-Team Core, restarts connectors, and verifies tool discovery. Takes 30-120s depending on skill count. Use after connector restarts, Core hiccups, or stale state. For incremental changes, prefer ateam_patch (which updates + redeploys in one step).

  Connector

• search_mcp_servers

  Swarm Tips — Aggregated AI Agent Activities

  [READ] Search the Layer 3 curated directory of MCP servers and agent-work tools. The directory has 30 entries across three vetting tiers — `first-party` (operated by the swarm.tips DAO), `vetted` (third-party, we've used + verified), `discovered` (cataloged from public sources, not yet exercised). Filter by `query` (substring vs name/description/tags), `category` (substring), and `tier`. Results sort first-party → vetted → discovered. The same directory powers swarm.tips/discover; this tool exposes it programmatically. Use this when an agent needs to find an MCP server for a capability (DeFi, search, browser automation, etc.) instead of an opportunity (which `discover_opportunities` covers).

  Connector

• switch_dannet_server

  dannet

  Switch between local and remote DanNet servers on the fly. This tool allows you to change the DanNet server endpoint during runtime without restarting the MCP server. Useful for switching between development (local) and production (remote) servers. Args: server: Server to switch to. Options: - "local": Use localhost:3456 (development server) - "remote": Use wordnet.dk (production server) - Custom URL: Any valid URL starting with http:// or https:// Returns: Dict with status information: - status: "success" or "error" - message: Description of the operation - previous_url: The URL that was previously active - current_url: The URL that is now active Example: # Switch to local development server result = switch_dannet_server("local") # Switch to production server result = switch_dannet_server("remote") # Switch to custom server result = switch_dannet_server("https://my-custom-dannet.example.com")

  Connector

• fetch_document_pages

  openregistry

  Return specific pages of a PDF in one of three formats: • format='pdf' - pdf-lib page slice, preserves the original text layer and fonts (no re-encoding). This is the ONLY format that gives you byte-exact, citation-grade content. Use this for financial numbers, legal quotes, and any answer requiring precision. • format='text' - raw extracted text from pdfjs. Machine-readable but NOT authoritative - OCR errors on bad-quality text layers can silently garble digits. Use only for summarisation / light reading, and cross-check numbers by re-fetching with format='pdf'. • format='png' - page rasterization via Cloudflare Browser Rendering, for documents with text_layer='none' (scanned PDFs). Phase 6 - may return 'not implemented' in current deployment. The response includes at most 100 pages (Anthropic document-block hard cap). Split larger ranges into multiple calls. Requires the document's bytes to already be cached - call fetch_document on the full document first if this is a new filing.

  Connector

• licium_discover

  Licium

  Browse and compare Licium's agents and tools. Use this when you want to SEE what's available before executing. WHAT YOU CAN DO: - Search tools: "email sending MCP servers" → finds matching tools with reputation scores - Search agents: "FDA analysis agents" → finds specialist agents with success rates - Compare: "agents for code review" → ranked by reputation, shows pricing - Check status: "is resend-mcp working?" → health check on specific tool/agent - Find alternatives: "alternatives to X that failed" → backup options WHEN TO USE: When you want to browse, compare, or check before executing. If you just want results, use licium instead.

  Connector

• ask_us_capital_markets

  AskNeedl

  Query SEC filings and financial documents from US capital markets and exchanges. This tool searches through 10-K annual reports, 10-Q quarterly reports, 8-K current reports, proxy statements, earnings call transcripts, investor presentations, and other SEC-mandated filings from US companies. Use for questions about US company financials, executive compensation, business operations, or regulatory disclosures. Limited to official SEC filings and related documents only.

  Connector

• ceevee_get_report

  CareerProof MCP

  Get report status and metadata (without PDF). Returns status (pending/processing/completed/failed), title, type, inputs, and summary. This is the polling tool for ceevee_generate_report — call every 30 seconds, up to 40 times (20 min max). When status='completed', download PDF with ceevee_download_report(report_id). If status='failed', relay error_message. If still processing after 40 polls, stop and give the user the report_id to check later. Free.

  Connector

• licium_discover

  Licium

  Browse and compare Licium's agents and tools. Use this when you want to SEE what's available before executing. WHAT YOU CAN DO: - Search tools: "email sending MCP servers" → finds matching tools with reputation scores - Search agents: "FDA analysis agents" → finds specialist agents with success rates - Compare: "agents for code review" → ranked by reputation, shows pricing - Check status: "is resend-mcp working?" → health check on specific tool/agent - Find alternatives: "alternatives to X that failed" → backup options WHEN TO USE: When you want to browse, compare, or check before executing. If you just want results, use licium instead.

  Connector

• get_signal_narratives

  SupplyMaven MCP Server

  Get plain-language explanations of active predictive signals. Each narrative explains the mechanism behind a signal — why the predictor leads the target, what economic logic connects them, and what the current reading implies. Designed for non-quantitative users who want to understand the 'why' behind each signal without reading F-statistics. Returns trigger context, predictor value, direction, and a narrative paragraph suitable for reports and briefings.

  Connector

• thinkneo_bridge_list_mappings

  ThinkNEO Control Plane

  List all active MCP ↔ A2A bridge mappings and translation statistics. Shows which MCP servers are mapped to which A2A agents, plus 30-day translation stats (total, success rate, average latency). Requires authentication.

  Connector

• thinkneo_bridge_mcp_to_a2a

  ThinkNEO Control Plane

  Bridge an MCP tool call to an A2A (Agent-to-Agent Protocol) agent. Maps MCP tool name and parameters to the A2A task format, enabling interoperability between MCP servers and A2A agents. Returns a ready-to-send A2A task object with full protocol compliance. Translates the MCP tool_name and arguments into an A2A task, sends it to the target A2A agent, waits for completion, and translates the response back to MCP format. Use this to make any MCP tool accessible to A2A agents (Google's agent ecosystem). Requires authentication.

  Connector

• get_word_synonyms

  dannet

  Find synonyms for a Danish word through shared synsets (word senses). SYNONYM TYPES IN DANNET: - True synonyms: Words sharing the exact same synset - Context-specific: Different synonyms for different word senses Note: Near-synonyms via wn:similar relations are not currently included The function returns all words that share synsets with the input word, effectively finding lexical alternatives that express the same concepts. Args: word: The Danish word to find synonyms for Returns: Comma-separated string of synonymous words (aggregated across all word senses) Example: synonyms = get_word_synonyms("hund") # Returns: "køter, vovhund, vovse" Note: Check synset definitions to understand which synonyms apply to which meaning (polysemy is common in Danish).

  Connector

• get_usage_stats

  Name Whisper — ENS Intelligence Layer

  Get usage statistics for this MCP server session. Returns tool call counts, success rates, and average latency.

  Connector

• atlas_get_candidate

  CareerProof MCP

  Get full candidate detail including parsed CV content and parse status. Use this to verify CV parsing is complete (status='completed') before starting analysis. Requires context_id and candidate_id from atlas_upload_candidate or atlas_list_candidates. Free.

  Connector

• upload_template

  Carbone MCP

  Upload and store a reusable Carbone template. Once uploaded, use render_document with the returned Template ID to generate documents from it. Supports versioning: multiple versions can live under a single stable Template ID, with deployedAt controlling which version is active. Accepted formats: DOCX, XLSX, PPTX, ODT, ODS, ODP, ODG, HTML, XHTML, IDML, XML, Markdown, PDF, and more.

  Connector

• get_signal_narratives

  supply-chain-intelligence

  Get plain-language explanations of active predictive signals. Each narrative explains the mechanism behind a signal — why the predictor leads the target, what economic logic connects them, and what the current reading implies. Designed for non-quantitative users who want to understand the 'why' behind each signal without reading F-statistics. Returns trigger context, predictor value, direction, and a narrative paragraph suitable for reports and briefings.

  Connector

• similar_to

  MCP Marketplace

  Find MCP servers that are semantically similar to a reference server. Use when a user picked a candidate but wants alternatives — e.g. 'like this but safer', 'like this but free', 'what else does this'. Reuses the catalog's gte-small embeddings: the reference server's embedding is the query vector. Returns servers sorted by cosine similarity (highest first), excluding the reference itself. Each result carries the same security/risk/pricing fields as search_servers so callers can immediately compare on `security_score`, `has_critical_findings`, and pricing.

  Connector

• analyze_text

  Toolora

  Run a complete readability + structure analysis on a piece of writing in one call. Returns Flesch Reading Ease, Flesch–Kincaid Grade, Gunning Fog Index, SMOG, Coleman–Liau, and ARI in a single result, plus word/sentence/paragraph counts, average sentence length, complex-word percentage, reading time, target audience label, and human-readable warnings. Use this whenever an agent has just generated or edited prose and needs to check whether it lands at the right reading level. One call replaces 4–6 separate readability lookups.

  Connector

• extract_pdf_text

  Toolora MCP Server

  Use this tool whenever the user shares, uploads, or references a PDF file and wants to read, summarise, search, or analyse its contents. Extracts all plain text from the PDF (base64-encoded). Returns text, page count, word count, and character count. Call this first before attempting any analysis of PDF content — e.g. 'summarise this PDF', 'what does this contract say', 'extract the data from this report'. Free, no API key, no signup; the file is processed in memory and never stored.

  Connector

• compare_versions

  Toolora

  Compare two versions of a text (before/after) and return readability + tone deltas. Returns full readability profile and tone scores for each version, plus signed deltas for Flesch Reading Ease, average grade level, word count, and each tone dimension. Includes a one-line verdict like 'Easier to read (+8.2 Flesch) · Lower grade level (-1.4) · Shorter (-42 words)'. Use this in a draft → revise loop so the agent can prove the edit actually improved things.

  Connector