"How to work with Cocos .csd files" matching MCP tools:

• preview_still

  clipkit

  Render a single frame of the current project to a PNG and return it as an image you can look at. This is how you check your work — in chat there is no other way to see what a composition actually looks like. Use it liberally: after composing, after edits, and at different times to inspect motion. Stills are FREE (credits are only spent by render_video). Pass `time` (seconds) to choose the frame; defaults to 0.

  Connector

• ateam_upload_connector

  ateam-mcp

  Upload connector code to Core and restart — WITHOUT redeploying skills. MERGES with the GitHub state at `ref` by default (default ref: 'dev'). Sending a partial file set ONLY overlays those files — the rest of the connector is preserved from GitHub. To fully replace the connector dir (historical behavior), pass replace:true. Modes: • github:true (no files) — deploy the GitHub state at `ref` as-is. • github:true + files:[] — GitHub state at `ref` as BASE, your files overlay on top (incoming wins). • files:[] (no github) — default MERGE with GitHub state at `ref`. Refuses if no GitHub base exists (no silent nuke). • files:[] + replace:true — full replace. Wipes connector dir + writes only the provided files. Use deliberately. Common traps this design prevents: • Pre-fix bug (2026-06-06): sending just ui-dist HTML wiped server.js + node_modules — connector broke until a full re-upload. Now: those files merge with the GitHub base. • Pre-fix bug: github:true silently read from `main` even when patches were on `dev`. Now: defaults to dev; pass ref:'main' to opt into the legacy path.

  Connector

• knowledge_query

  dialogbrain

  Answer questions using knowledge base (uploaded documents, handbooks, files). Use for QUESTIONS that need an answer synthesized from documents or messages. Returns an evidence pack with source citations, KG entities, and extracted numbers. Modes: - 'auto' (default): Smart routing — works for most questions - 'rag': Semantic search across documents & messages - 'entity': Entity-centric queries (e.g., 'Tell me about [entity]') - 'relationship': Two-entity queries (e.g., 'How is [entity A] related to [entity B]?') Examples: - 'What did we discuss about the budget?' → knowledge.query - 'Tell me about [entity]' → knowledge.query mode=entity - 'How is [A] related to [B]?' → knowledge.query mode=relationship NOT for finding/listing files, threads, or links — use search.files / search.threads / search.links for that.

  Connector

• moxie.get_documentation_patterns

  Moxie Docs

  Get Moxie's summary of how THIS repository organizes and maintains documentation - where docs live relative to code and how they are kept current. Read-only; no side effects. Returns a Markdown list of pattern entries, each with a title, explanation, and source citations. Use this to decide WHERE a new doc should go before calling propose_doc_update; for the list of WHICH docs need work, use get_documentation_opportunities instead.

  Connector

• tfgenerate

  InsideOut (Riley)

  WORKFLOW: Step 3 of 4 - Generate Terraform files from completed design Generate Terraform files from an InsideOut session that has completed infrastructure design. ⚠️ PREREQUISITE: Only call this AFTER convoreply returns with `terraform_ready=true` in the response metadata. DO NOT call this while convoreply is still running or before terraform_ready is confirmed! If you get 'session has not reached terraform-ready state', wait for convoreply to complete first. 🎯 USE THIS TOOL WHEN: convoreply has returned with terraform_ready=true, OR the user asks to 'see the terraforms', 'generate terraform', 'show me the code', etc. **DEFAULT RESPONSE**: Returns summary table + download URL (keeps code out of LLM context). **FALLBACK**: Set `include_code: true` to get full code inline if curl/unzip fails. **CRITICAL WORKFLOW** (default mode): 1. Call this tool to get file summary and download URL 2. ASK the user: 'Where would you like me to save the Terraform files? Default: ./insideout-infra/' 3. WAIT for user confirmation before running the download command 4. Run the curl/unzip command with the user's chosen directory 5. If curl/unzip FAILS (sandbox, security, platform issues), retry with `include_code: true` **AFTER GENERATION**: Ask user if they want to review the files and then deploy with tfdeploy REQUIRES: session_id from convoopen response (format: sess_v2_...). OPTIONAL: include_code (boolean) - set true to return full code inline as fallback. 💡 TIP: Examine workflow.usage prompt for more context on how to properly use these tools.

  Connector

• explain_architecture

  Zephex

  Maps how files connect across a subsystem — roles and import edges, not file bodies. Ripgrep + import-graph analyzers; detects framework, language, architecture_type. Envelope: focus, summary, hint, data, related_focus, next_calls, meta (meta.cache_hit, meta.tokens_returned, meta.credits, meta.charges_usage). Hosted: 7 credits per success; failures free. Cheapest path: mode overview + concern or seed_files — ~1.5–4k tokens, replaces 10+ blind read_code file opens. Repeat identical calls hit server cache (meta.cache_hit) until force:true. Expensive: mode deep or audit on whole monorepo — use subpath. >10k files auto-degrades to overview. data: entry_points, layer_map, concern_cluster (with concern or seed_files[]), integration_map, auth_flow, dependency_graph; deep adds request_flows + Mermaid; audit adds anti_patterns + health_score. dimension_confidence per slice; warnings on low confidence. focus: api|auth|integrations|database|security|data_flow|error_handling|full. Pass concern (any label) or seed_files[] (1–20 from find_code). subpath scopes monorepos. Call BEFORE cross-cutting edits — how a feature spans modules, where to patch. Do NOT for stack (get_project_context), search (find_code), bodies (read_code), tests, packages, live URL. After: next_calls → read_code outline on hub files. Read-only.

  Connector

• update_site

  vibedeploy

  Patch or replace files on an existing site. Defaults to patch mode: only the listed files change; everything else stays. Pass mode:'replace' to wipe-and-replace the whole site (the legacy behaviour, surfaced explicitly so it can't happen by accident). Use `delete: [paths]` in patch mode to remove specific files without wiping the rest. Use `dryRun: true` to preview the diff before committing. LARGE FILES: a 100-250 KB text file fits in one call with encoding:'gzip+base64' (gzip locally, base64 the result) — prefer that over begin_deploy + add_file_chunk streaming. Errors if the site does not exist.

  Connector

• get_pm_playbook

  AIOProductOS MCP

  How to operate as a product manager on AIOProductOS. No arguments and no side effects — returns the same operating guide as plain text every call (deterministic): how to ground in the product brain, keep work welded to the spine (insight→feature→task→outcome), prioritise on evidence (affected accounts + MRR + reach), and what 'done' means. Call it FIRST, before planning or prioritising, to load the house rules the other tools assume.

  Connector

• upload_assets

  AppDeploy

  Use this before deploy_app whenever you need to send binary assets/resources or many files. Prefer this whenever the source of truth already exists as local files or a local project tree, especially for multiple files or whole-file replacements. This is the required path for images, backgrounds, icons, fonts, PDFs, media, archives, and other file assets you want deployed. Prepare local files and the upload manifest first. Call upload_assets only when you can upload immediately. If the upload_url expires before use or the upload fails because it expired, call upload_assets again to get a fresh upload_url and upload_id. PUT multipart/form-data to the returned upload_url: a 'payload' part (JSON manifest with text file changes/diffs and deletePaths) plus binary files named by app-relative path. The upload manifest carries all text changes and diffs plus deletePaths. After upload succeeds, call deploy_app with upload_id only. Do not also send files[] or deletePaths[]; those changes belong in the upload manifest. Never base64-encode binary assets into deploy_app.

  Connector

• get_guide

  Tu Lugar

  Curated TuLugar guides (general education, kept current): buying-process (step-by-step + documents), foreigners (rights + restrictions for non-Paraguayans), closing-costs (what fees exist), renting (contracts, deposits, garante), publishing (listing tips), airbnb (short-term rental basics). ALWAYS use this for "how does buying/renting work" / process / documents questions — the content IS in scope to share; only personalized legal advice is not.

  Connector

• get_project_context

  main

  Captures the user's project architecture to inform i18n implementation strategy. ## When to Use **Called during i18n_checklist Step 1.** The checklist tool will tell you when to call this. If you're implementing i18n: 1. Call i18n_checklist(step_number=1, done=false) FIRST 2. The checklist will instruct you to call THIS tool 3. Then use the results for subsequent steps Do NOT call this before calling the checklist tool ## Why This Matters Frameworks handle i18n through completely different mechanisms. The same outcome (locale-aware routing) requires different code for Next.js vs TanStack Start vs React Router. Without accurate detection, you'll implement patterns that don't work. ## How to Use 1. Examine the user's project files (package.json, directories, config files) 2. Identify framework markers and version 3. Construct a detectionResults object matching the schema 4. Call this tool with your findings 5. Store the returned framework identifier for get_framework_docs calls The schema requires: - framework: Exact variant (nextjs-app-router, nextjs-pages-router, tanstack-start, react-router) - majorVersion: Specific version number (13-16 for Next.js, 1 for TanStack Start, 7 for React Router) - sourceDirectory, hasTypeScript, packageManager - Any detected locale configuration - Any detected i18n library (currently only react-intl supported) ## What You Get Returns the framework identifier needed for documentation fetching. The 'framework' field in the response is the exact string you'll use with get_framework_docs.

  Connector

• explain_queueing_theory

  QueueSim

  Return a ~500-word educational explainer of M/M/c queueing theory: Little's Law, utilization, why averages mislead, how simulation relates to Erlang-C. No inputs. Use this when the user asks a conceptual 'why' or 'how does this work' question rather than asking for a number.

  Connector

• get_about

  Follow On Tours

  Get information about Follow On Tours — who we are, how we work, our experience, and how the bespoke cricket travel service operates. Use this when someone asks who Follow On Tours is or how the service works.

  Connector

• axint.project.index

  Axint

  Scan the local Apple project and write a compact .axint/context pack so Axint can reason over changed files, nearby SwiftUI surfaces, and interaction-risk files instead of only one source file at a time. Use: use before project-aware repair, multi-file SwiftUI work, or interaction-risk analysis. Inputs: changedFiles seed related-file discovery; dryRun returns the pack without writing .axint/context. Effects: writes .axint/context unless dryRun=true; reads local project files only.

  Connector

• estimate_cost

  AiDOOS Virtual Delivery Center

  Use this tool when a user wants cost or sizing for specific deliverables they've already listed. Trigger phrases: 'how much would it cost to build X, Y, and Z', 'estimate the price for these features', 'how many Delivery Units / weeks would these modules take', 'budget for this work', 'price out this scope', 'I need a ballpark for the following'. Use this INSTEAD OF plan_vdc when the user has already decomposed the work into specific modules — don't make them go through pod/role generation again. If the user only describes a goal without modules, prefer plan_vdc. What this tool does: takes 1-30 module descriptions, returns Delivery Units per module, total Delivery Units, project-rate USD cost, and the recommended Delivery Pack (Starter 10 DUs/$2K, Small 60 DUs/$10K, Scale 250 DUs/$40K, or Enterprise).

  Connector

• list_files

  Dock

  List the folder + file children of a Files surface (kind='files'). Folders sorted first by position then name; files sorted by name. Returns folders[], files[] with cuids agents can pass to `get_file` / `delete_file`. `parent_folder_id` defaults to null (= root of the surface); pass a folder id to descend into a sub-folder. Gated behind FILES_SURFACE_ENABLED + per-user allowlist (in beta on socrates@vector.build; other accounts get -32000 'not available').

  Connector

• get_sc_theory

  SCModeling

  Reference guide to supply-chain simulation concepts: ordering policies, BOM, FDD formulas, event-driven simulation. Pure static text — no engine call, deterministic output. Use this when the user asks a conceptual 'how does this work' question rather than asking for a number.

  Connector

• orcid_get_works

  orcid-mcp-server

  Retrieve works associated with an ORCID iD — publications, datasets, software, preprints, and more. Returns work summaries with put-codes, titles, types, publication dates, journal names, and all external identifiers (DOIs, PMIDs, arXiv IDs, ISBNs). The first 50 works are returned by default; workCount reports the total available, and prolific records are paged with offset and the returned nextOffset (or raise limit). Set include_external_ids to false to omit identifier lists for a lighter payload. Pass the putCode from each work to orcid_get_work_detail to retrieve the full record including abstract and contributors. External IDs are ready for chaining to Crossref, PubMed, or arXiv servers. Works are self-reported; a researcher may not have linked all their publications.

  Connector

• get_model

  Civitai

  Get full details for a single Civitai model by id — description, type, creator, tags, download/rating stats, and every version with its base model, trigger words and downloadable files. Try id 4201 ("Realistic Vision V6.0 B1", a SFW checkpoint). Defaults Safe-For-Work; nsfw flag is surfaced. Keyless.

  Connector

• get_platform_info

  mcp

  Get high-level facts about the ACCRUE platform: fee structure, custody model, supported chains, wallets, KYC requirements, withdrawal terms, and AI agent integration status. Use this when the user asks "what is ACCRUE", "how does ACCRUE work", "what are the fees", or anything about the platform itself rather than a specific vault.

  Connector