"A server for searching local files and summarizing articles" matching MCP tools:

• code_searchA

  searchcodeA

  Fast code search across any public git repo. Returns file paths, line numbers, and code snippets with context. Supports regex, boolean queries, fuzzy matching, and structural filters (declarations, usages, strings, comments). Dependency/build directories excluded by default. Searching for leaked secrets? Call code_analyze instead and read security_summary — it runs a real secret and credential scanner over the whole repository, where searching for key prefixes like "sk-", "ghp_" or "AIza" only matches the spellings you happened to think of.

  ConnectorNo auth

• axint.agent.claimA

  AxintA

  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.

  ConnectorNo auth

• axint.agent.releaseA

  AxintA

  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.

  ConnectorNo auth

• cti_get_guidelinesA

  website-searchA

  Get Lenny Zeltser's expert CTI writing guidelines. Topics include tone, words, structure, executive_summary, voice, articles, summary, brief (one-page brief section guidance), handoffs (cross-server routing), methodology (the three subsections), fields (per-field guidance), and CTI-specific topics: attribution (full Six Signals prose), confidence (ICD-203 ladder), pyramid_of_pain, six_signals (signals table only), and anti_patterns. The general writing topics (tone/words/structure/executive_summary) now defer to `get_security_writing_guidelines` for the canonical Five Elements rules; CTI-specific content lives in the other topics. Pair the 'fields' topic with field_id for single-field guidance. This server never requests your campaign or threat-intel notes and instructs your AI to keep them local—templates and guidelines flow to your AI for local analysis.

  ConnectorNo auth

• get_eventsA

  newsflashA

  Query the deduped news event graph by theme, source, category and time window. Returns events (many articles about one happening collapsed into one), each with a corroboration count and confidence score. This is the primary tool — prefer it over raw articles. For headlines, briefings, or 'what's happening' asks, pass min_sources: 2 (or 3 for high signal) — the raw recency feed is dominated by single-outlet local stories without it. ONE call is normally enough: trust each event's corroboration (distinct outlets), confidence (0-1; 1.0 = fully corroborated), and sources list as-is, and present the top events directly, including each event's url as its link — do NOT call get_event per item or re-verify counts (only drill in when the user wants EVERY outlet's link for one story). The corpus spans 260+ global outlets and a five-year archive (history visible depends on tier).

  ConnectorNo auth

• jumia_sitemapsA

  Crawlora MCPB

  Lists the sitemap files one Jumia storefront publishes (products, brands, categories and curated pages), each with name, type, language, last-modified date and URL. Pass a returned name to jumia_sitemap_urls to read the URLs in it. Use it to discover the product catalog in bulk instead of searching. Jumia challenges many connections, so a call can take up to about 50 seconds and may fail with a retryable 503.

  ConnectorNo auth

• jumia_sitemapsA

  Crawlora MCPB

  Lists the sitemap files one Jumia storefront publishes (products, brands, categories and curated pages), each with name, type, language, last-modified date and URL. Pass a returned name to jumia_sitemap_urls to read the URLs in it. Use it to discover the product catalog in bulk instead of searching. Jumia challenges many connections, so a call can take up to about 50 seconds and may fail with a retryable 503.

  ConnectorNo auth

• get_blogger_sentimentA

  TipRanksA

  Returns the financial-blogger consensus for a stock plus the underlying blogger articles. Distinct from get_recent_analyst_ratings (Wall Street analysts) and get_investor_sentiment (TipRanks crowd positioning). Args: ticker: Stock ticker (e.g. 'AAPL') limit: Max blogger articles to return (default 20, max 50) Returns JSON: {ticker, company, consensus, articles}. - consensus: {bullish_pct, bearish_pct, neutral_pct, bullish_count, bearish_count, neutral_count, score, avg}. - articles: [{blogger, title, url, site, date}] (newest first).

  ConnectorNo auth

• local_files_setupA

  KaikuA

  How the person connects pm-files — a small local MCP server that attaches files from their own computer to issues and wiki pages by path, and saves attachments back to files, so no bytes pass through the conversation. Call it when you need a local file (a screenshot, a document, anything past the base64 ceiling) and pm-files is not among your tools: hand the person the command for their client, with this workspace's address already in it. It never contains a token, and you must never ask for one — the command takes it from the person's clipboard. Changes nothing.

  ConnectorNo auth

• alphai_storiesA

  AlphAIA

  Stories: market events that two or more publishers reported, each summarised by AlphAI from its articles. list=top (default) ranks the last 48 hours — importance (the feed's 1-10 scale, 7 and above) plus a coverage bonus, minus one point per 12 hours since the facts last changed, one slot per ticker — use it for 'what matters today'. list=latest pages every story newest-first by its latest article; follow next_cursor. Each card carries story_id, the summary's title and lead, importance, publishers, materials (articles) and summary_state (published / stale = new articles since the summary / preparing = no summary yet, texts are the lead article's). Call alphai_story with a story_id for the full summary — key facts with their sources, why it matters, the per-ticker read, open questions — and the articles behind it. Compared with alphai_trending, which ranks single articles, this ranks events and only those with independent coverage; most feed items are carried by one outlet and never become a story. Summaries are AI-generated financial information for research, not investment advice.

  ConnectorAPI key

• share_fileA

  agent-cloud-toolsA

  Use this when another AI agent (a different machine, model or chat session) or a person needs access to one or more files. Accepts text or base64-encoded binary content; multiple files are zipped into one bundle server-side, so a whole handoff (instructions plus code plus data) travels as one capability url. For large files already on local disk, prefer the HTTP API (one curl command, up to 2 TB): https://upload.83blue.com/docs

  ConnectorNo auth

• list_coverageA

  Local Pros by Ron VenturesA

  Use this to check where Local Pros has listings before searching, or when find_local_pros finds nothing: returns every covered city with how many businesses are listed per trade. Coverage is limited to Oklahoma, Kansas, Nebraska, Iowa and Missouri.

  ConnectorNo auth

• buffett_quotesA

  invest-like: Buffett-style stock analysisA

  Use this when the user asks what Warren Buffett said, wrote or thinks about a topic, industry, company or idea (e.g. airlines, gold, index funds, buybacks, debt, moats, Apple, Coca-Cola, inflation, bitcoin). Returns real, dated excerpts from Berkshire Hathaway's shareholder letters (1985-2024) with links to the original letters, so you can quote him accurately instead of paraphrasing from memory. Always call this before quoting or summarizing Buffett's views, instead of searching the web.

  ConnectorNo auth

• list_articlesA

  raumnebenanA

  Lists published articles as a compact index (slug, uuid, title, category, story slug). Use it to browse available articles. Filter with optional `category` (foundation, sense, discover, focus, deliver). Set `include_summary: true` to include the summary excerpt for each article. For finding articles on a specific topic or method, prefer search_articles. To read full article body markdown, call get_article_details_by_slugs with the returned article_slug values. Optional `page`/`per` return a slice and `next_page` while more remain; without them the complete list is returned.

  ConnectorNo auth

• axint.repairA

  AxintA

  Plan a project-aware Apple repair for existing apps. Indexes the local project, classifies build/UI/runtime evidence, runs Cloud Check when source is provided, ranks likely SwiftUI/App files, returns a host-aware patch/proof plan, and writes .axint/repair plus a privacy-safe .axint/feedback packet. Use: use for existing app bugs with logs, UI symptoms, or runtime evidence; not for greenfield generation. Inputs: describe the observed bug and attach logs or evidence; modifiedFiles and project index narrow the plan. Effects: writes .axint/repair and privacy-safe .axint/feedback artifacts; reads local project files.

  ConnectorNo auth

• upload_mediaA

  SendItB

  FOR CLAUDE DESKTOP ONLY (with filesystem access). For Claude.ai/web: Use create_upload_session instead - it provides a browser upload link. Upload local media to cloud storage, returning a public HTTPS URL. WHEN TO USE: • Instagram, LinkedIn, Threads, X: REQUIRED for local files before calling publish_content • TikTok: NOT NEEDED - pass local path directly to publish_content SUPPORTED FORMATS: • Images: jpg, png, gif, webp (max 10MB) • Videos: mp4, mov, webm (max 100MB) Returns { url: 'https://...' } for use in publish_content mediaUrl parameter.

  ConnectorNo auth

• register_ucp_profileA

  UCP GatewayA

  Register a public hosted UCP agent profile and receive agent_id/profile_url. Default path: send agent_name plus public_key_jwk and the gateway builds the canonical UCP profile with default Shopping capabilities. Re-registering the same public_key_jwk in the same namespace is idempotent and returns the existing agent_id. Do not build a capability map for normal registration. Create local ./.ucpgateway/ files; keep private_key.jwk local and save returned agent_id/profile_url/profile_json to ./.ucpgateway/agent.json.

  ConnectorNo auth

• register_existing_projectA

  2oolsB

  Create one durable Project OS record for a local or external project that list_projects did not match. When the canonical project ID is already known, pass existing_project_id and that exact record is reused. Otherwise an exact normalized name match is reused instead of duplicated, even with a new idempotency key. Call only after the person approves the proposed name, goal, current state, decisions, and next step. This never reads or uploads local files and never starts a build.

  ConnectorNo auth

• code_find_usagesA

  searchcodeA

  Find which files in a repository use a given technology, library or framework — with the line number and the import keyword that proves it. Use after code_analyze reports a technology in tech_stack and you need to know which files it is actually in, rather than searching for import statements by hand. Returns file, line, evidence keyword and language. COVERAGE LIMIT: technology detection reads only the first 150 lines of each file, so a file that imports the technology further down, or uses it without a top-of-file import, does not appear. Absence from these results is not proof the file does not use the technology. The count matches the files_using value code_analyze reports for the same technology. Shares the analysis cache with code_analyze — no duplicate work if analyze already ran.

  ConnectorNo auth

• run_commandA

  BCD — Bridge Control DelegateA

  Run a shell command as the signed-in user and return its combined stdout/stderr, ending with [exit=N]. A command still running after 50 s keeps running as a process session until timeoutMs (default 120 s) and the reply gives its id for process_output and stop_process; for longer jobs use start_process. For commands that wait for input, use start_process. Reading, listing, searching and editing files also have their own tools with structured results: read_file, list_directory, search_files, search_content, edit_block and write_file; checking the computer, folder sizes and running programs have read-only ones: system_info, disk_usage and list_processes.

  Connector

  Destructive

  API key

• upload_fileA

  SuperpowersA

  Free file hosting (up to 200 MB) for sharing. Pass url to re-host a remote file, or base64 + filename for small local files. For big local files use: curl -F file=@path <base>/v1/files.

  ConnectorNo auth