"A server for interacting with a large language model chat" matching MCP tools:

• generate_image

  Avocado AI

  Generate an AI image using Avocado AI. Returns a jobId immediately; image generation completes in 10-60 seconds. After calling, use the check_job tool with the returned jobId to retrieve the result, once complete, check_job returns the image inline so it renders directly in chat. Run models_list to see available models. Costs 1-4 credits per image depending on model and quality.

  Connector

• tm_import_rvt

  Twinmotion MCP

  Import a Revit/BIM model into the Twinmotion visualization pipeline: downloads the source file from a public URL, uploads it to an APS OSS transient bucket, and kicks off an SVF2 + thumbnail translation job. Returns the base64 URN (project_id) used by every other tm_* tool. When to use: when a user wants to prepare a Revit (.rvt), IFC (.ifc), or other BIM/CAD model for real-time visualization in Unreal Engine / Twinmotion — typically the first step before rendering stills, defining scenes, or exporting FBX/glTF/OBJ geometry for a UE import. Also use when you need thumbnails or view metadata from a source file that has not yet been translated by APS. When NOT to use: not for MEP clash review (use navisworks-mcp), not for quantity takeoff or cost estimation (use qto-mcp), not for Twinmotion presets editing — Twinmotion itself has no public REST API, so scene/material authoring must happen manually in the UE editor after FBX/USD export. APS scopes required: data:read data:write data:create bucket:read bucket:create viewables:read. Uses Model Derivative API (translation) + OSS (upload). Twinmotion has no public REST API; all automation is APS Model Derivative + manual Unreal Engine export. Rate limits: APS default ~50 req/min per app per endpoint; Model Derivative translation jobs ~60 req/min; large .rvt/.nwd/.ifc files are often multi-GB and translation can take 5–60 min — poll the manifest with exponential backoff (start 5s, cap 60s) rather than retrying this tool. Worker request ceiling is ~100MB body; extremely large files may need signed-URL upload instead. Errors: 401 = APS token failed (check APS_CLIENT_ID/APS_CLIENT_SECRET, re-auth); 403 = scope missing (bucket:create/data:write not granted — have user re-consent); 404 = file_url unreachable; 409 = bucket key collision (rare — retry, tool uses timestamp); 413/507 = file too large for worker memory (advise signed-URL upload); 422 = unsupported source format (only Autodesk-accepted types: rvt, ifc, nwd, dwg, dgn, 3dm, stp, etc.); 429 = back off 60s before retrying; 5xx = APS upstream outage, retry with backoff. Side effects: CREATES a new transient OSS bucket (scanbim-viz-<timestamp>, auto-expires in 24h), CREATES an object in OSS, STARTS a translation job consuming APS cloud credits. NOT idempotent — each call creates a new bucket + URN. Writes a row to usage_log D1 table.

  Connector

• upload_image

  Real Real Genuine

  Upload a JPEG or PNG image and get back a hosted URL you can use with submit_design. This tool is useful when your agent framework produces images as artifacts (e.g. base64 strings) and you need to upload them before submitting a design. Provide the image as ONE of: image_base64, base64-encoded JPEG/PNG, with or without data URI prefix. image_url, publicly accessible image URL (max 5 MB). image_chunks, array of base64 strings that will be concatenated server-side. Use this if your base64 string is too large for a single parameter. Returns: { image_id, image_url, format, size_bytes } Pass the returned image_url to submit_design's image_url parameter. ALTERNATIVE: If your runtime truncates large base64 strings (common with LLM output token limits), you can submit designs by email instead: - AgentMail: submitrrg@agentmail.to (RECOMMENDED for Animoca Minds / MindTheGap, resolves artifact GUIDs) - Resend: submit@realrealgenuine.com Attach the image as JPEG/PNG. Subject: "RRG: Title". Body: wallet: 0x...

  Connector

• transcribe_translate

  Sats4AI - Bitcoin-Powered AI Tools

  Compound endpoint — one payment turns audio in any of 13 source languages into both a transcript AND a translation in any of 119 target languages. Perfect for WhatsApp voice messages in a language you don't speak (Yoruba → English), or recording a meeting in another language and reading it in yours. Auto-detects source if omitted. Async — returns requestId, poll with check_job_status(jobType='transcribe-translate'). Flat price covers STT + translation. Cheaper than calling transcribe_audio + translate_text separately for typical voice messages. Pay with Bitcoin Lightning — no API key or signup needed. Requires create_payment with toolName='transcribe_translate'.

  Connector

• analyze_company

  Nordic Financial MCP

  AI-powered company analysis using semantic search over Nordic financial data. Orchestrates multiple searches internally and returns a synthesized narrative answer with source citations. Covers annual reports, quarterly reports, press releases and macroeconomic context for Nordic listed companies. Use this when you want a synthesized answer rather than raw search chunks. For raw data access, use search_filings or company_research instead. For a full due diligence report with AI-planned sections, use the Alfred MCP server: alfred.aidatanorge.no/mcp Args: company: Company name or ticker question: What you want to know about the company model: 'haiku' (default) or 'sonnet'

  Connector

• get_interconnection_queue

  DC Hub — Data Center Intelligence MCP Server

  ISO interconnection queue snapshot: total queued GENERATION capacity (queued_load_total_gw, GW) per ISO from each ISO's public queue. For ERCOT it ALSO returns the large-load (data-center-driven) interconnection queue in queued_load_data_center_gw — >225 GW in process / ~9 GW approved-to-energize (ERCOT's published Q1-2026 figure; ERCOT is the only ISO that publishes a comparable large-load feed, so other ISOs' data_center_gw is null), with provenance in top_subregions. Sources: ERCOT GIS + Large Load Integration, PJM/MISO/SPP/CAISO/NYISO/ISO-NE public queues. Pass iso=ERCOT (or any of 7) to drill down. Use for queue-depth site-selection and AI/data-center-load saturation intel (the ERCOT 225 GW number is the headline large-load figure no other source surfaces machine-readably). Do NOT use for a single-site time-to-power read (use get_grid_intelligence) or forward-looking emergence (use grid_transition_radar); this is the ISO-level queue snapshot.

  Connector

• convert_from_url

  Botverse

  Offload a document conversion to Botverse — runs server-side in seconds, returns a download link, and frees you to continue with other tasks while it processes. Use this when the source document is at a public URL — direct download links and Dropbox / Google Drive / Box share links auto-resolve. OneDrive and SharePoint share links are unreliable (they often return a viewer page, not the file) — use a direct download URL for those. If you already have the content as a string, use convert_content instead — no upload step needed. Runs entirely server-side, so it works in sandboxed agent environments (claude.ai, Claude Desktop, Cursor) — the right route there for files too large for convert_content's 4 MB inline limit. Supported inputs: md, html, rst, txt, docx. Supported outputs: docx (Word), pdf, html, txt, md, rst, xlsx (tables extracted). Returns a job_id immediately. Poll get_job_status every 5s until 'complete', then get_output_content (inline, sandbox-safe) or get_download_url (S3 link). Flat fee $0.05 per file.

  Connector

• upload_media

  switch

  Upload one image into your Switch library in a single call. Pass `url` (any public https) OR `base64` + `mime`. Switch fetches/decodes it server-side, stores it, and returns a clean public URL plus the new asset id. This is THE way to use a photo the user attached in chat as a reference: pass the returned `url` directly into generate_image's reference_image_urls, OR into generate_video's image_url (image-to-video) or reference_image_urls (reference / omni video). The returned URL is provider-fetchable as-is — no presigned PUT, no curl, no confirm-upload step. Do NOT call get_my_active_references for a chat-attached photo; that strip only holds Studio-managed refs.

  Connector

• plan_deploy

  mcp

  Turns YOUR repo classification (you scan the repo and pass what you found) into a complete, approvable deploy plan WITHOUT creating anything: picks the VM + managed-Postgres sizes, prices them at the real pricing_rules rates, and checks they FIT your quota — so a plan that can't provision is caught HERE, before any spend. You pass what you detected in the repo (runtime, port, needs_postgres/redis/vector_db); it returns resources + £/hr + £/mo + a feasibility verdict + a checkpoint summary to confirm with the user. Defaults: app VM m1.medium, managed Postgres m1.small; pass single_vm to collapse onto one VM. Only Postgres is auto-provisionable today — Redis / vector-DB needs are flagged, not provisioned. Any containerizable app works (node, python, go, ...) — it deploys as a container, so the language doesn't gate it. Set serves_http:false for a non-web repo (a library, CLI, or language runtime with no HTTP server) and it returns a clean not-a-web-service verdict instead of a costed VM plan. Set heavy_build:true for resource-heavy builds (compiled-from-source native code, a monorepo/turborepo build, a large Node heap) and it raises the app VM to a build-capable floor so the on-VM build doesn't get OOM-killed. Also returns a brand-named markdown report (Mermaid diagram + cost) to save as redu-deploy-plan.md and show the user.

  Connector

• open_sutta_viewer

  Tripitaka MCP (hosted)

  Open an interactive sutta viewer inside the chat — Pāli + English, plus an optional third row in the user's own language translated BY YOU. Renders each segment as: Pāli on top (canonical), the Bhikkhu Sujato English below it (verification anchor), and — when you supply `translations` — your translation in the user's language, clearly badged as AI-generated. Prefer this over dumping raw segments when the user wants to *read* a sutta. - `sutta_id` — standard SuttaCentral id, e.g. `sn56.11`, `mn10`, `dn22`. - `around` — a segment_id (e.g. `dn22:18.1`, from a search hit) to centre on; that segment is highlighted and scrolled into view. Use this after a search so the reader lands on the exact cited line. - `offset` — 0-based segment index for paging long suttas (use `next_offset` from the previous result). Do NOT combine with `around`. - `window` — segments before/after `around` to include (default 12). 🌐 **Translating for the user (important):** when the conversation language is neither English nor Pāli, you SHOULD translate the displayed segments and pass them via `translations` so the user reads in their own language while still seeing the originals: 1. Fetch the segments first (`get_sutta` with the same selector) so you have the exact Pāli + English text. (Already called this tool without translations? The result contains the segments — translate them and call this tool AGAIN with the same selector plus `translations` to upgrade the view.) Your translation must travel through the `translations` parameter to appear in the viewer — writing it as a normal chat message leaves the viewer bilingual and looks broken; the tool always accepts `translations`, so never report it as missing. 2. Translate **from the Pāli as the source, using the English as a semantic guide** — never relay-translate from English alone. Preserve untranslatable doctrinal terms (dukkha, jhāna, taṇhā…) as loanwords with a brief gloss instead of forcing equivalents. 3. Call this tool with `translations=[{segment_id, text}, ...]` covering ONLY the segments being displayed (never a whole long sutta), `translation_language` (BCP-47, e.g. "th", "es"), and `translation_disclaimer` — one short line IN THE USER'S LANGUAGE saying the translation is AI-generated in this conversation and should be checked against the Pāli/English above. Translations are conversation-ephemeral: nothing is stored server-side; the canon stays Pāli + English only. Translations whose segment_id is not in the displayed window are dropped (reported in `translations_dropped`). Without `around`, shows the sutta from the top (capped for long suttas).

  Connector

• render_preview

  kernelcad

  Use this when you need to LOOK at a kernelCAD model — render its script to deterministic PNG views for visual self-check (the visual half of the evaluate → render → inspect → fix loop), with NO studio or dev server required. Pass { code } (inline source) or { file } (a .kcad.ts path), exactly one. Renders the canonical engineering views (front, right, top, iso — pass { views } for a subset, e.g. ["iso"] for fastest iteration) plus an optional { pose: "<az>,<el>" } arbitrary camera angle (degrees; az=0,el=0 is front, +az rotates CCW around +Z, +el lifts the camera). NO STUDIO / DEV-SERVER REQUIRED: a prebuilt static player (dist/headless-player) is served from an ephemeral local port automatically; a running studio dev server is used as fallback, and { base_url } forces one. The only environment dependency is playwright chromium (npx playwright install chromium). Pass { focus } or { hide } (arrays of feature ids or assembly part names, mutually exclusive) to isolate parts — same semantics as `kernelcad render --focus/--hide`. PNGs are written to { out_dir } (default: a fresh temp session directory) and returned as absolute paths with per-view camera descriptions (kernelCAD is Z-up). Mechanism truth runs first, same protocol as `kernelcad render`: a broken mechanism still renders but every tile is watermarked MECHANISM BROKEN (KERNELCAD_RENDER_STRICT=1 refuses instead); read { mechanism, mechanism_failure_codes }. The probe runs full BREP interference sweeps and can dominate latency on large assemblies — pass { no_mechanism_check: true } for fast iteration (the preview then reports mechanism: "unverified"; ignored under strict mode). Returns { ok, images: [{ name, path, description }], out_dir, bounds, mechanism, render_source, render_ms, diagnostics }. PATHS ARE LOCAL to the machine running the MCP server — local stdio clients read them directly; hosted/remote clients should use open_in_studio instead.

  Connector

• get_latest_render

  kernelcad

  Render a project's current model server-side and return it as an inline image so you can SEE what you built. Use this after open_in_studio (or any /p/<slug> link): call with that `slug` to inspect whether the build looks right. CRITICAL — the image is rendered from the MODEL on the server; it does NOT reflect the user's Studio camera, zoom, or screen. NEVER ask the user to rotate, zoom, pan, move the camera, close a slider, or change their view to help you see — you cannot affect their screen and it cannot affect this render. To see a different angle, call this tool again with a different `view`. By DEFAULT (omit `view`, or `view:"all"`) it returns a CONTACT SHEET of all six canonical views in one labeled image — a 3×2 grid, top row [iso, front, right], bottom row [back, left, top] — so you can judge the model from every side regardless of its orientation (e.g. to find which side has the doors). Pass a single `view` (iso/front/back/left/right/top) for one large render of that angle. DETERMINISTIC: the same model + view always returns the same bytes — identical bytes are NOT a stale/lagging snapshot. If you changed the model, push it with open_in_studio FIRST, then re-render to see the change. The image is always current and never a blank capture. Colors and shading match Studio (same palette / base-material color). The slug is the capability: no OAuth for public/unlisted; private projects require the owner signed in. The PNG is base64-inlined as a real image block by default; pass `paths_only: true` for metadata only. No renderable geometry or a mesh failure → { ok: false, error, hint }, never a blank image.

  Connector

• set_language

  mailopoly

  Set the user's preferred language for the emails, reports and app content Mailopoly sends them — a BCP-47 code like 'es', 'fr', 'de', 'pt', 'ja', 'ar', 'zh', 'ru'. Call this ONCE, early, as soon as you can tell from the conversation which language the user actually speaks/writes (e.g. they message you in German → call set_language('de'); their first request is in Arabic → set_language('ar')). This does NOT change how you reply in this chat — it makes their Mailopoly emails and website render natively, which they otherwise can't tell you because they never see English here. If the user clearly uses English, just skip it (English is the default). Takes effect immediately and never overrides a language the user picked themselves in Mailopoly's settings.

  Connector

• nwd_get_clashes

  Navisworks MCP

  Detect geometric/logical clashes between two element sets in an already-translated Navisworks model. Uses APS Model Derivative property extraction + same-level proximity heuristics, optionally augmented by VDC rules stored in D1 (table vdc_rules). When to use: when coordinating federated MEP + structural + architectural models for clash review before issuing an RFI; e.g. "find duct vs. beam clashes on Level 3 before the Wed coordination meeting" or "sanity-check the latest MEP revision against structure before releasing for fabrication." Pair with nwd_export_report to produce a deliverable. When NOT to use: do not call on a model whose translation is still "inprogress" — call nwd_export_report first and confirm translation_status == "success"; not a substitute for Navisworks Manage Clash Detective for final sign-off (this is a coordination-stage screen, not a regulatory clash report). APS scopes required: viewables:read data:read (read-only — does not create anything in APS). Rate limits: APS default ~50 req/min per endpoint; Model Derivative metadata/properties endpoints are the bottleneck. Properties response may return 202 "isProcessing" on first call — the worker retries once after 3s. For very large models (>50k elements) the worker caps analysis at 50x50 element cross-compare and 100 reported clashes; re-run with tighter category_a/category_b filters for exhaustive coverage. Errors: 401 APS token expired (transient, retry); 403 missing viewables:read/data:read scope (report, do not retry); 404 URN not found or not translated (prompt user to re-run nwd_upload); 409 not applicable; 422 model translated but property index unavailable — typically means source NW version unsupported or translation partially failed (supported: Navisworks 2015+); 429 rate limit (backoff); 5xx APS upstream (retry once). If properties.data.collection is empty the tool returns clash_count: 0 with a note rather than erroring — the agent should treat that as "model not ready" and retry later. Side effects: none in APS. Reads vdc_rules from D1 when both categories are supplied. Logs usage to D1 usage_log. Idempotent — same inputs on a stable model yield the same clash list.

  Connector

• company_search

  Drillr — The financial MCP for AI agents

  Use for qualitative company discovery (industry, business model, supply chain, competitors, management background). For numerical screening (revenue, margins, ratios, growth rates) use run_sql on company_snapshot instead. Drillr's company knowledge base — searchable across industry classification, product offerings, business model, segment structure, competitive landscape, supply chain, management background, and customer profile. Pass a natural language description (e.g. "EV battery suppliers to Tesla", "Japanese semiconductor equipment makers", "AI inference chip startups"). Returns a structured list of matching companies with context snippets. ONLY for finding a LIST of companies by description.

  Connector

• cover_letter_tool

  Workopia

  Write a cover letter for a SPECIFIC job — TWO steps. STEP 1 (default; action omitted or 'prepare'): the server returns the job's JD and the candidate's background, plus writing instructions. YOU (the model) then WRITE the cover letter (250–350 words, specific to the role, mapping the candidate's real achievements to the JD — never fabricate). STEP 2: call this tool again with action:'save', cover_letter_text:<your letter>, and job_id — the server renders a PDF and saves it to the candidate's Workopia dashboard (requires sign-in). Use whenever the user asks for a cover letter for a specific job. Resolving job_id (same rules as tailor_resume_tool / job_detail_tool): pass the **Job Id** value from the most recent prior search/refine result VERBATIM; no placeholders like 'JOB_1' or '#1'. For STEP 1 supply ONE of job_id (preferred — server fetches the JD from Mongo) OR job_description, plus the candidate's resume via resume_text / resume_content / json_resume / user_profile.

  Connector

• list_saved_sites

  DC Hub — Data Center Intelligence MCP Server

  Use when a user asks to see or review their saved DC Hub shortlist in-chat (FREE with a key). Example: "What sites have I saved?" / "Show my shortlist." — list_saved_sites. Params: none. Returns: an array of saved sites, each with name, market, lat/lon, saved DCPI score, target MW, and notes — the persistent shortlist built by save_site. Do NOT use to add a site (use save_site) or to download the list as a file (use export_dataset); this is the in-chat read-back.

  Connector

• tm_render_image

  Twinmotion MCP

  Render a still preview image of the model at a specified resolution by pulling the APS Model Derivative thumbnail (capped at 800x800 by the APS endpoint). Also resolves the camera_preset against model metadata to identify which 3D view it maps to, and applies any stored environment config from tm_set_environment for reference. When to use: when you need a quick visual sanity-check of an imported model (e.g. 'show me what Tower A looks like'), to preview a specific named view before committing to a full UE/Twinmotion render, or to embed a low-res preview in a chat/report. Pair with tm_list_scenes first to discover valid view names/GUIDs. When NOT to use: not for production-quality renders (APS thumbnails are low-res and raster-only; for cinematic output use Unreal Engine Movie Render Queue after FBX/USD export), not for arbitrary custom camera angles (only named views from the source file are resolvable — there is no runtime camera placement API here), not for 2D sheet exports (use tm_list_scenes to find 2D roles and fetch directly). APS scopes required: viewables:read data:read. Hits Model Derivative thumbnail + metadata endpoints only. Rate limits: APS default ~50 req/min per app per endpoint. Thumbnail endpoint is usually fast (<2s) once the model has translated; if called while status='inprogress' it returns no thumbnail. Do not loop-poll this tool — poll the manifest via tm_set_environment or tm_list_scenes instead. Errors: 401/403 = token/scope; 404 = URN not found or thumbnail not yet generated (model still translating — retry after manifest reports success); 409 = n/a; 422 = n/a; 429 = back off 30s; 5xx = APS upstream. Side effects: NONE (read-only on APS). Reads KV env_config_<urn>. Writes a row to usage_log. Idempotent.

  Connector

• ai

  Fast.io

  Ripley — the MCP delegation surface over Fastio's RAG agent. Ripley is read-only for storage CONTENT: it answers natural-language questions about workspace/share files & folders (with citations) and never creates/edits/deletes your files — for content writes, call the primitive MCP tools directly. It DOES create/manage chat threads (chat-create/chat-update/chat-delete/message-send) and can generate shares (share-generate). Prefer Ripley over issuing many primitive reads: ask one NL question and let the server-side agent search + synthesize. Quick start: action='ask' (question + profile) → returns {answer_text, citations, chat_id, message_id, web_url}; action='status' for an engineered workspace-status summary. Lower-level chat/message actions remain for multi-turn control. Call action='describe' for the full action/param reference. Destructive: chat-delete. Side effects: ask/status/chat-create/message-send consume credits; chat-cancel terminates an in-progress message (partial tokens billed; idempotent). Verbosity (detail param): chat-list/message-list default to terse (compact rows). chat-details/message-details default to full (drill-down). Pass an explicit detail='standard'|'full' to override (best-effort: chat/message/activity endpoints may not yet honor detail server-side).

  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