bxc-mcp-author

A guide for building and updating bxc-style MCP servers, which let AI assistants use tools provided by other programs. It covers registering tools, defining their inputs, building the server, and connecting it to Claude and Gemini.

In plain words
What is it for?
Use it to add or modify tools in bxc-native-mcp, including tools that call bxc packages, X/Grok clients, web scrapers, or Rust code.
Why use it?
It gives a consistent way to add tools without overlooking the server build, manifest, configuration, or documentation changes needed to make them available.

Agent

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add agents/aphrody-code/bxc/bxc-mcp-author
Clone the repo
git clone --depth 1 https://github.com/aphrody-code/bxc
Per session 78 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 379 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00078 $0.00379
Opus 5 $0.00039 $0.00189
Sonnet 5 $0.00016 $0.00076
Haiku 4.5 $0.00008 $0.00038

Measured 2d ago against content hash e7283f73c73f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

bxc-mcp-author scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

plugins/bxc/agents/bxc-mcp-author.md · 24 lines

What it actually says

You are the specialist for the bxc-native-mcp (the stdio MCP server that powers Claude + Gemini with bxc capabilities).

When asked to add or modify a tool:

  1. Edit src/mcp/server.ts (or the equivalent in a ported project).
  2. Use server.registerTool(name, { description, inputSchema: z.object(...) }, handler).
  3. Export the tool name in the manifest/gemini-extension if needed.
  4. Update the build (bun run build:mcp).
  5. Add usage examples to the relevant bxc skill (bxc-mcp-server).
  6. If the tool calls into Rust FFI or X/Grok native clients, coordinate with the bxc-rust-ffi-engineer and bxc-x-grok-architect agents.
  7. For the plugin: keep the example .mcp.json and docs up to date with ${CLAUDE_PLUGIN_ROOT} / ${CLAUDE_PROJECT_ROOT}.

Always keep the server lightweight and the tool results concise (JSON or markdown suitable for LLM context).

See the canonical implementation in the bxc repo and the bxc-mcp-server skill for patterns.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 24 lines · 78 tokens per session scan A e7283f73c73f

Subscribe to this mod's changes

bxc-mcp-author is an agent published in the GitHub repository aphrody-code/bxc (2 stars, last pushed 2d ago), licensed Apache-2.0. It adds 78 tokens to every session and 379 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other agents, from other repositories

web-navigator

Navigation subagent over tandem's shared Chrome. Use it ONLY for HEAVY read/extraction (large snapshots, scraping, walking many pages) without live human interaction. It isolates the noise (DOM, snapshots) in its own context and returns only the distilled data. Do NOT use it when there are walls the human must clear…

bgmacris/quimera-ai · 92 tokens

project-manager

Project manager for CrawlForge MCP Server development. Coordinates tasks, delegates to specialized sub-agents IN PARALLEL, tracks progress, and ensures clean implementation. Use PROACTIVELY for any multi-step project coordination.

mysleekdesigns/crawlforge-mcp · 46 tokens

security-auditor

Security specialist for CrawlForge MCP Server. Audits code for vulnerabilities, ensures secure practices, validates input sanitization. Use PROACTIVELY before deployments and after major changes.

mysleekdesigns/crawlforge-mcp · 40 tokens

{{APP_NAME}}-builder

Maintain and extend the {{APPNAME}} MOAB automation — add features, re-mine broken selectors, and upgrade the server. Privileged; use deliberately, not for day-to-day automation.

zmustafa/MOAB-Automations · 46 tokens

consultant

Evoflux is an open-source, local-first workspace where AI agents build software, conduct deep research, automate browser tasks, and collaborate in parallel. Connect any model, keep control of your workspace and data, and take complex work from idea to completion—all in one place.

evoelsewhere/evoflux · 2 tokens

executor

Evoflux is an open-source, local-first workspace where AI agents build software, conduct deep research, automate browser tasks, and collaborate in parallel. Connect any model, keep control of your workspace and data, and take complex work from idea to completion—all in one place.

evoelsewhere/evoflux · 1 tokens