FreePublished on GitHub

mcp

Plan abi MCP server work — the 12-tool JSON-RPC 2.0 stdio surface plus its custom loopback HTTP compatibility listener. Use for abi-mcp, tools, transports, or middleware.

The English summary is being prepared. Showing the original description.

donaldfilimon/abi19 stars(GitHub 19 + cccskills 0)

Run score Not tested

See how to install

Files included (1)

SKILL.md3.1 KB

SKILL.md (original)

Review the instructions the agent will receive before you install.

mcp

Entry point for the abi MCP server (crates/abi-mcp/src/). Routes to specialists:

You want to…	Use
Smoke-test abi-mcp + verify the 12-tool contract	`mcp-smoke`
Deep-dive the MCP superpower	`abi-superpower-mcp`
Transport / middleware / protocol limits detail	`abi-mcp-transport`

Frozen contract (do not change without a parity/contract-test update)

12 tools, in source order: ai_run, ai_complete, ai_learn, ai_train, wdbx_query, scheduler_stats, scheduler_info, connector_test, gpu_status, plugin_list, wdbx_stats, plugin_run.
protocol.MAX_REQUEST_SIZE = 64 KB; MAX_JSON_DEPTH = 32; per-field 16 KB cap in crates/abi-mcp/src/middleware.rs (declarative validation before dispatch).
Frozen enums: connector_test tool arg service ∈ {openai, anthropic, discord, twilio, grok}; ai_train tool arg format ∈ {jsonl, csv, text}.

Honest boundary

Stdio exits on stdin EOF (not a long-lived daemon). Startup also attempts the custom loopback listener (127.0.0.1:8080 by default, configured with ABI_MCP_HTTP_PORT / ABI_MCP_HTTP_TOKEN); bind failure leaves stdio running. GET /sse opens a persistent MCP 2024-11-05 HTTP+SSE session whose POST /message?sessionId=<id> responses arrive as SSE message events (202 on the POST; unknown session 404; at most 16 sessions), while POST /message without a session keeps the one-shot direct-reply mode. It is not Streamable HTTP (2025-03-26), and non-loopback serving is not supported. Rust handlers return bounded JSON-RPC errors without exposing internal error chains.

Client registrations (cleaned 2026-09): consistent across grok/claude/codex/opencode/cursor + abi project scopes. Use launcher for abi-mcp everywhere. See opencode and help skills for the exact current lists.

Finalized state (2026-09-16)

Best options: central only ~/.grok/skills + launch.sh sync (idempotent, 0 on re-run); donald-mode; bot-repo authority separate (abbey-bot etc); permission fixes in opencode.jsonc + .grok/config.toml; key comments (GITHUB_TOKEN="", disabled with # requires KEY).
Global MCPs standardized: .cursor/mcp.json, .claude.json, ~/.grok/config.toml [mcp_servers.*], ~~/.config/opencode/opencode.jsonc — core: abi-mcp (via /.../abi/mcp/launcher.sh stdio), skill-loop@0.3.3, context7, fetch(uvx), filesystem(~~/.abi/), github(unauth), memory, playwright. (4 more disabled w/ comments).
Verifs: central sync-clis.py --dry-run = "0 actions/changes"; abi in-repo .agents/skills/sync-clis/launch.sh --dry-run (separate mech); mcp-smoke.sh = "RESULT: PASS — 12/12"; configs parse clean; no drift (timestamps match, dry=0); key files re-read (abs paths).
Maintain: ALWAYS edit only central ~/.grok/skills/* (or .grok/config.toml for grok MCPs); run sync; never hand-edit copies. Abbey-bot/others: own AGENTS/CLAUDE, separate.
No loose ends. All per context + final re-checks.

Reviews

No reviews yet. Tell others what you thought.

Comments

No login needed. Share how it worked for you, ask a question, or note where it did not run.

No comments yet. Be the first to write one.

More skills from this repository

abbey-system-prompt

Free

Maintain the Abbey / Aviva / Abi Discord system prompts in the Rust abbey-bot (`src/ask.rs`) and keep the hosted Grok bots (Grok Bot Abbey, Aviva Grok) in step with them. Use when the user says "improve grok bots", "abbey prompt", "persona prompt", "ask.rs", "system prompt", "tip floor", asks to change how Abbey/Aviva/Abi speak on Discord, or after an abbey-bot PR merges and the hosted bot's tip floor needs bumping. Runs as /abbey-system-prompt.

The English summary is being prepared. Showing the original description.

donaldfilimon/abi19Updated Oct 27, 2026

abi-claims-validator

Free

Validate ABI docs and external collateral against repo evidence and docs/contracts/external-claims-audit.mdx. Use when auditing claims, scanning docs for unsupported QPS/sharding/FHE/AES language, checking one claim before publish, or re-confirming the external-claims audit. Agent procedure only — not a CLI or slash command. Pair with abi-doc-claims-sync when editing docs.

The English summary is being prepared. Showing the original description.

donaldfilimon/abi19Updated Oct 27, 2026

abi-doc-claims-sync

Free

Synchronize ABI Markdown and docs claims with executable behavior. Use before editing README, AGENTS.md, CLAUDE.md, GEMINI.md, docs/**/*.mdx, walkthroughs, changelogs, or any old ABI Markdown that mentions WDBX, MCP, GPU, clustering, compression, FHE, agents, or benchmarks.

The English summary is being prepared. Showing the original description.

donaldfilimon/abi19Updated Oct 27, 2026

abi-goal-orchestrator

Free

Plan and execute ABI repo work from the TODO board, roadmap/spec docs, stable Rust 1.99.1 constraints, and validation gates. Use when the user asks to find ABI todos/roadmaps, organize a large implementation from tasks/todo.md, or decide the next safe work slice. Distinct from the goals skill — that skill owns the persistent ledger tasks/goals.md; this skill plans from the active board and north-star specs.

The English summary is being prepared. Showing the original description.

donaldfilimon/abi19Updated Oct 27, 2026

abi-mcp-transport

Free

Validate ABI MCP JSON-RPC stdio and its custom loopback HTTP compatibility endpoint, including auth, limits, notifications, and shutdown.

The English summary is being prepared. Showing the original description.

donaldfilimon/abi19Updated Oct 27, 2026

abi-plugin-system

Free

Review ABI's 16 compiled-in plugin fixtures, manifest validation, manual bundled registry, and real CLI/MCP run dispatch without claiming dynamic loading.

The English summary is being prepared. Showing the original description.

donaldfilimon/abi19Updated Oct 27, 2026

See all skills by donaldfilimon

Report a problem with this skill

Install

Install with a command

npx skills add https://github.com/donaldfilimon/abi --skill mcp

Paste it into your terminal and run it (requires Node.js). You can choose which agents to install it for, such as Claude Code or Codex.

Ask your agent

Please install the following Agent Skill.
https://github.com/donaldfilimon/abi/tree/main/.claude/skills/mcp

First review SKILL.md and the bundled files and confirm there is nothing suspicious (such as sending data externally or reading credentials). Then place it in ~/.claude/skills/mcp/ for Claude Code, or ~/.agents/skills/mcp/ for Codex.

Send this text to Claude Code or Codex as is. It checks the contents before installing.

View source on GitHub

Repository: donaldfilimon/abi
Stars: 19
Forks: 4
Category: Development
License: Apache-2.0
Original language: English
Last updated: Oct 27, 2026

A skill is a set of instructions and scripts for an agent. cccskills does not guarantee that skills are safe. Review the contents before you install.