"Installing MCP (Minecraft Coder Pack) servers into an IDE" matching MCP tools:

• validate_pythonA

  CodeCraftA

  Validates a Python automation script that runs OUTSIDE the game, on three axes: Python syntax (using the real interpreter), Minecraft commands embedded in the script (against the official command index), and the shape of the /connect WebSocket message envelope. For behavior pack scripts use validate_script instead — Python does not run inside a pack. The embedded command check is the most valuable one: a command written from memory can look syntactically fine and still do nothing in the game. Only strings starting with / are treated as commands. If syntax could not be checked, syntaxChecked is false in the result; ok:true alone does not mean the syntax is valid.

  ConnectorNo auth

• get_project_contextA

  XMemoB

  Read one authorized project's bounded context pack: state, TODOs, decisions, timeline, recent memories, and optional durable recall. Requires memory:read; it does not mutate project memories, and access is audit-logged. Use an exact project_id for a whole-project snapshot; otherwise use recall_context. max_items/max_tokens bound the whole pack; recent_hours affects only timeline; durable_query requires include_durable_context.

  ConnectorOAuth

• start_pack_buildA

  vera.inkA

  Start a paid asynchronous pack build after the user explicitly approves max_credits. Supply exactly one of pack_id (an owned AI-buildable pack) or new_pack. The response returns immediately with job_id; poll get_pack_build_status only while active=true. max_credits is a hard ceiling, not a promised final charge. Reuse idempotency_key only for an exact retry.

  ConnectorNo auth

• start_pack_buildA

  vera.inkA

  Start a paid asynchronous pack build after the user explicitly approves max_credits. Supply exactly one of pack_id (an owned AI-buildable pack) or new_pack. The response returns immediately with job_id; poll get_pack_build_status only while active=true. max_credits is a hard ceiling, not a promised final charge. Reuse idempotency_key only for an exact retry.

  ConnectorNo auth

• chieflab_approve_actionA

  ChiefLabA

  [chieflab_* alias of chiefmo_approve_action] Approve one ChiefMO publish/send action so its executor can fire. USE WHEN the user — in IDE chat — said 'approve <channel>' (e.g. 'approve linkedin', 'approve hn'), 'approve all', 'ship it', 'go ahead', or otherwise greenlit a specific draft you rendered. Match the user's words to the channel, look up agentGuide.renderInChat[channel].actionId from the launch response, and call this tool with that actionId. This is the IDE-native approval path — no need to push the user to the reviewUrl. Pass `actionId` (preferred) or `id` (legacy alias). P74: pass `autoExecute: true` AND the connector inputs (`platforms` for social / `recipients` + `subject` for email) to have the approval chain directly into execution — approve and ship in one tool call. Without autoExecute (or when connector is manual_handoff / blocked), the response includes executionPlan and the caller is expected to invoke the suggestedTool next.

  ConnectorNo auth

• chieflab_approve_actionA

  ChiefLabA

  [chieflab_* alias of chiefmo_approve_action] Approve one ChiefMO publish/send action so its executor can fire. USE WHEN the user — in IDE chat — said 'approve <channel>' (e.g. 'approve linkedin', 'approve hn'), 'approve all', 'ship it', 'go ahead', or otherwise greenlit a specific draft you rendered. Match the user's words to the channel, look up agentGuide.renderInChat[channel].actionId from the launch response, and call this tool with that actionId. This is the IDE-native approval path — no need to push the user to the reviewUrl. Pass `actionId` (preferred) or `id` (legacy alias). P74: pass `autoExecute: true` AND the connector inputs (`platforms` for social / `recipients` + `subject` for email) to have the approval chain directly into execution — approve and ship in one tool call. Without autoExecute (or when connector is manual_handoff / blocked), the response includes executionPlan and the caller is expected to invoke the suggestedTool next.

  ConnectorNo auth

• supply_chain_checkA

  Presend MCP ServerA

  Call this before installing or adding a package (npm install, pip install, a new entry in a manifest), especially one whose name you recalled or that a model suggested. One-call risk check: combines vulnerability_check (OSV.dev), typosquat_check, maintainer_change_check (npm only) and repo_health_check (when the GitHub repo can be resolved) into one overall verdict. A package that does not exist on npm or PyPI gets overall_risk 'package_not_found': the name may be invented and should not be installed. A package first published less than 30 days ago gets the 'new_package' flag and overall_risk 'review_recommended': new packages are where invented and look-alike names get registered, so the name is worth confirming against the project's own documentation before installing (on PyPI the age is that of the oldest release still published; being new does not make a package malicious). Use the individual tools to investigate one signal. Vulnerabilities are checked for the given version, or the latest published one (version_checked, version_source). If a check could not run (rate limit, upstream error), it is listed in unavailable_checks and overall_risk is 'incomplete', never 'no_signals_found'. Also flags a version marked deprecated on npm or yanked on PyPI.

  ConnectorNo auth

• start_lowpoly_generateA

  Retro Diffusion Pixel ArtA

  Start building a low-poly 3D model with pixel-art textures from a prompt and/or reference images (paid). reference_models puts your existing models (by asset_id) into it exactly, e.g. "a tavern with my table". Optional input_palette (a palette image, as for create_inference): the model uses only its colors, and revisions and animations keep them. Returns task_id and asset_id immediately; poll get_lowpoly_job(task_id) until it succeeds (usually 1-5 minutes). Then use export_lowpoly_model for .glb/.bbmodel/Minecraft/OBJ files, start_lowpoly_revise to change it, or start_lowpoly_animate to add motion. Failed jobs are refunded automatically; never restart a running job.

  ConnectorNo auth

• start_lowpoly_generateA

  Retro Diffusion Pixel Art MCPA

  Start building a low-poly 3D model with pixel-art textures from a prompt and/or reference images (paid). reference_models puts your existing models (by asset_id) into it exactly, e.g. "a tavern with my table". Optional input_palette (a palette image, as for create_inference): the model uses only its colors, and revisions and animations keep them. Returns task_id and asset_id immediately; poll get_lowpoly_job(task_id) until it succeeds (usually 1-5 minutes). Then use export_lowpoly_model for .glb/.bbmodel/Minecraft/OBJ files, start_lowpoly_revise to change it, or start_lowpoly_animate to add motion. Failed jobs are refunded automatically; never restart a running job.

  ConnectorNo auth

• android_install_apkA

  DialogBrainB

  Install an app on the Android device from an APK or split bundle (XAPK/APKS — how most large modern apps ship). Provide apk_url (an https link the device downloads itself — preferred, and the only workable option for real apps) or, for tiny payloads, as apk_base64. Max 300MB. Large apps can take several minutes; if this call times out the install keeps running on the device — verify with the app-list tool instead of re-installing. Use reinstall=true to uninstall then install (for signature changes).

  Connector

  Destructive

  API key

• android_install_apkA

  dialogbrainB

  Install an app on the Android device from an APK or split bundle (XAPK/APKS — how most large modern apps ship). Provide apk_url (an https link the device downloads itself — preferred, and the only workable option for real apps) or, for tiny payloads, as apk_base64. Max 300MB. Large apps can take several minutes; if this call times out the install keeps running on the device — verify with the app-list tool instead of re-installing. Use reinstall=true to uninstall then install (for signature changes).

  Connector

  Destructive

  API key

• android_install_apkA

  dialogbrainB

  Install an app on the Android device from an APK or split bundle (XAPK/APKS — how most large modern apps ship). Provide apk_url (an https link the device downloads itself — preferred, and the only workable option for real apps) or, for tiny payloads, as apk_base64. Max 300MB. Large apps can take several minutes; if this call times out the install keeps running on the device — verify with the app-list tool instead of re-installing. Use reinstall=true to uninstall then install (for signature changes).

  Connector

  Destructive

  API key

• diagnose_crashA

  ModkeelA

  Find the mod most likely behind a modded Minecraft crash (Fabric, NeoForge, Forge). Use it whenever the user shares a crash report or latest.log or says the game will not start. It is the only tool that reads logs, and it adds what the file does not hold: it checks every installed mod against the Modkeel lab (pairs in the pack that clashed, jars that crashed on that Minecraft version), says how many other players hit the same crash and which fix worked for them (when 10+ did), counts lab runs of each suspect, and ranks suspects by evidence (mixin, trace, missing class) with a confidence level (NONE when nothing points at a mod). It also returns a fix guide and, when the log names the Minecraft version and loader, the build to install for the suspect and for every installed mod the lab saw crash on that version, so no follow-up call is needed. Pass the whole file as text, unedited: trimming it loses the mod list; or, when the user gave a link to a paste (mclo.gs, pastebin.com, paste.ee, gist.github.com, modkeel.com), pass url instead and Modkeel fetches it. Text with no crash in it comes back as an error to fix and retry. Up to 4 MB; read and dropped, never stored.

  ConnectorNo auth

• report_problemA

  Pizza DeveloperA

  Report a problem with Pizza Developer itself (the app, not a project tracked inside it) on behalf of the signed-in vibe coder. Never send one on your own initiative: first show the vibe coder the exact `message` and `path`, and call only after they explicitly confirm that report, passing userConfirmed: true. A report cannot be read back, edited, or withdrawn once sent. Pass `path` when it is about a particular page (`/projects/{id}`), and say plainly in `message` what went wrong and what was expected. Docs: https://pizzadeveloper.com/docs/report-a-problem

  ConnectorNo auth

• supply_chain_checkA

  Presend dependency checksA

  Call this before installing or adding a package (npm install, pip install, a new entry in a manifest), especially one whose name you recalled or that a model suggested. One-call risk check: combines vulnerability_check (OSV.dev), typosquat_check, maintainer_change_check (npm only) and repo_health_check (when the GitHub repo can be resolved) into one overall verdict. A package that does not exist on npm or PyPI gets overall_risk 'package_not_found': the name may be invented and should not be installed. A package first published less than 30 days ago gets the 'new_package' flag and overall_risk 'review_recommended': new packages are where invented and look-alike names get registered, so the name is worth confirming against the project's own documentation before installing (on PyPI the age is that of the oldest release still published; being new does not make a package malicious). Use the individual tools to investigate one signal. Vulnerabilities are checked for the given version, or the latest published one (version_checked, version_source). If a check could not run (rate limit, upstream error), it is listed in unavailable_checks and overall_risk is 'incomplete', never 'no_signals_found'. Also flags a version marked deprecated on npm or yanked on PyPI.

  ConnectorNo auth

• search_modsA

  ModkeelA

  Turn a mod's display name or part of its id into the exact mod id the other lab tools take, and see which mods the Modkeel lab has data on. Use it first when you only have a name ("Entity Culling", "Sodium") or are unsure of the id; skip it when you already have the id. To download a mod, call find_mod_download with its name instead: it finds the mod itself. Matching ignores case, spaces and punctuation; best match first, then the mods with more lab data. An empty query lists every mod the lab tested. Returns each mod's id, the Minecraft versions it was tested on and how many runs and pairs it has, plus the total number of matches. No match means the lab has no data on that mod, not that it is broken (get_mod_info still finds it on Modrinth by slug). mc keeps only mods with a run on that exact version; limit caps the list, and total says how many matched.

  ConnectorNo auth

• get_mod_infoA

  ModkeelA

  What one Minecraft mod is and where to get it: its Modrinth page (title, summary, categories, loaders, the Minecraft releases its author lists, client/server side, licence, downloads, source and issue links) next to a short Modkeel lab record (tested versions, run and pair counts). Use it for "what does this mod do?", "is it client-only?", "where do I download it?" or to link a suspect from diagnose_crash. The versions here are what the author declares; for what the lab saw run or crash, use get_mod_runs, and for two mods together, check_mod_pair. Takes a lab mod id or a Modrinth slug; from a name, call search_mods first. The project is matched by the SHA-1 of a jar the lab ran (source: jar_hash, exact), else by slug (source: slug); a mod on neither returns found: false, not an error. Asks Modrinth live on each call (nothing cached here), so it can fail when Modrinth is down: retry later.

  ConnectorNo auth

• pack_createA

  RokhaB

  Requires a JWT (never an rk_ key). Create — or retitle, keyed by slug — a PACK of items you own: slug (lowercase, digits, - _; ≤60), title (≤120), description (≤2000). Then add items with pack_items_set and price the pack with product_set {kind:'pack', ref:<pack id>, model, price_cents}. A pack with no price grants nothing. You keep 80% of each pack sale.

  ConnectorNo auth

• write_own_theme_filesA

  WhizzyCommerceB

  Write several files of an own theme at once: `changes` maps a path to its whole new content, or null to delete it. Pass the revision you last read as baseRevision; if the theme changed since, nothing is written. The theme is checked first: a write that would leave it not installing saves nothing and says why. Changes the theme's files only, not the shop: stage_own_theme puts them on the shop as its draft.

  Connector

  Destructive

  OAuth

• write_own_theme_filesA

  WhizzyCommerceB

  Write several files of an own theme at once: `changes` maps a path to its whole new content, or null to delete it. Pass the revision you last read as baseRevision; if the theme changed since, nothing is written. The theme is checked first: a write that would leave it not installing saves nothing and says why. Changes the theme's files only, not the shop: stage_own_theme puts them on the shop as its draft.

  Connector

  Destructive

  OAuth

• get_store_template_detailsA

  agentViewA

  Returns full details of one store template: localized title and description, long-form markdown, category, suite, tags, features, preview image and agentArtifacts (bot-onboarding files such as system prompts, Agent Skills SKILL.md, MCP config). Use after search_store_templates before recommending or installing; when agentArtifacts is non-empty, fetch bodies via get_agent_artifact. No authentication required.

  ConnectorNo auth