Archivebox Api

CLI or API | MCP | Agent

Version: 1.0.1

Documentation — Installation, deployment, usage across the API, CLI, MCP, and A2A agent interfaces, and guidance for provisioning the ArchiveBox platform are maintained in the official documentation.

Related MCP server: Rexi MCP Server

Table of Contents

• Overview

• Key Features

• Concept Registry

• Environment Variables

• CLI or API Usage

• MCP Server Setup

• Agentic AI Graph Agent

• Security & Governance

• Installation

• Contribute

Overview

Archivebox Api is a production-grade Agent and Model Context Protocol (MCP) server designed to interface directly with the Pythonic ArchiveBox API Wrapper and Fast MCP Server for Agentic AI use!

Key Features

• Consolidated Action-Routed MCP Tools: Minimizes token overhead and eliminates tool bloat in LLM contexts by grouping methods into optimized, togglable tool modules.

• Enterprise-Grade Security: Comprehensive support for Eunomia policies, OIDC token delegation, and granular execution context tracking.

• Integrated Graph Agent: Built-in Pydantic AI agent supporting the Agent Control Protocol (ACP) and standard Web interfaces (AG-UI).

• Native Telemetry & Tracing: Out-of-the-box OpenTelemetry exports and native Langfuse tracing.

Concept Registry

This codebase is aligned with the 5 Core Pillars Architecture of the agent-utilities ecosystem:

Environment Variables

Package environment variables

Inherited agent-utilities variables (apply to every connector)

23 package + 12 inherited variable(s). Auto-generated from .env.example + the shared agent-utilities set — do not edit.

Configure the runtime environment by creating a .env file based on .env.example. Every variable the server reads, grouped by concern.

Connection & Credentials

MCP server / transport

Tool toggles

Each action-routed tool can be disabled individually via its toggle env var (set to false): AUTHENTICATIONTOOL, CORETOOL, CLITOOL (see the Available MCP Tools table below).

Telemetry & governance

Agent CLI (full [agent] runtime only)

CLI or API Usage

You can use the API client programmatically in Python to manage ArchiveBox snapshots:

from archivebox_api import Api

# Initialize client
client = Api(
    url="http://localhost:8000",
    token="your-auth-token",
    verify=True
)

# Fetch snapshots
snapshots = client.get_snapshots()
for snapshot in snapshots.get("results", []):
    print(f"[{snapshot['timestamp']}] {snapshot['url']}")

Refer to docs/index.md for full developer SDK and class references.

MCP Server Setup

Install the slim [mcp] extra. Install archivebox-api[mcp] — the MCP-server extra that pulls only the FastMCP / FastAPI tooling (agent-utilities[mcp]). It deliberately excludes the heavy agent runtime (the epistemic-graph engine, pydantic-ai, dspy, llama-index, tree-sitter), so uvx/container installs are dramatically smaller and faster. Use the full [agent] extra only when you need the integrated Pydantic AI agent (see Installation).

This server utilizes dynamic Action-Routed tools to optimize token overhead and maximize IDE compatibility.

Tool Catalog

See the auto-generated Available MCP Tools table below for the full, live list of tools.

Dynamic Tool Selection & Visibility

This MCP server supports dynamic toolset selection and visibility filtering at runtime. This allows you to restrict the set of exposed tools in order to prevent blowing up the LLM's context window.

You can configure tool filtering via multiple input channels:

• CLI Arguments: Pass --tools or --toolsets (or their disabled counterparts --disabled-tools and --disabled-toolsets) during startup.

• Environment Variables: Define standard environment variables:

  • MCP_ENABLED_TOOLS / MCP_DISABLED_TOOLS

  • MCP_ENABLED_TAGS / MCP_DISABLED_TAGS

• HTTP SSE Request Headers: Pass custom headers during transport initialization:

  • x-mcp-enabled-tools / x-mcp-disabled-tools

  • x-mcp-enabled-tags / x-mcp-disabled-tags

• HTTP SSE Request Query Parameters: Append query parameters directly to your transport connection URL:

  • ?tools=tool1,tool2

  • ?tags=tag1

When query strings or parameters are supplied, an LLM-free Knowledge Graph resolution layer (using DynamicToolOrchestrator) matches query intents against known tool tags, names, or descriptions, with safe fallback and automated 24-hour background cache refreshing.

Local IDE Configuration (Cursor / Claude Desktop)

Add the following block to your mcp.json to configure stdio transport via uvx:

{
  "mcpServers": {
    "archivebox-api": {
      "command": "uv",
      "args": [
        "run",
        "--package",
        "archivebox-api",
        "archivebox-mcp"
      ],
      "env": {
        "ARCHIVEBOX_BASE_URL": "http://localhost:8000",
        "ARCHIVEBOX_USERNAME": "admin",
        "ARCHIVEBOX_PASSWORD": "your-password"
      }
    }
  }
}

Agentic AI Graph Agent

This repository features a fully integrated Pydantic AI Graph Agent. It communicates over the Agent Control Protocol (ACP) and interacts seamlessly with the Agent Web UI (AG-UI).

Running the Agent CLI

To start the interactive command-line agent:

# Export credentials
export ARCHIVEBOX_BASE_URL="http://localhost:8000"
export ARCHIVEBOX_USERNAME="admin"
export ARCHIVEBOX_PASSWORD="your-password"

# Run agent server
archivebox-agent --provider openai --model-id gpt-4o

Detailed graph node architecture explanations, custom skill configurations, and agentic trace guides are available in docs/index.md.

Security & Governance

Built directly upon the enterprise-ready agent-utilities core, standard security parameters are fully supported:

Access Control & Policy Enforcement

• Eunomia Policies: Fine-grained, policy-driven tool authorization. Supports none, local embedded (mcp_policies.json), or centralized remote modes.

• OIDC Token Delegation: Compliant with RFC 8693 token exchange for flowing authenticating user credentials from Web UI / ACP → Agent → MCP.

• Scoped Credentials: Execution context runs restricted to the specific caller identity.

Runtime Security Grid

Installation

Pick the extra that matches what you want to run:

# MCP server only (recommended for tool hosting — slim deps)
uv pip install "archivebox-api[mcp]"

# Full agent runtime (Pydantic AI + epistemic-graph engine)
uv pip install "archivebox-api[agent]"

# Everything (development)
uv pip install "archivebox-api[all]"      # or: python -m pip install "archivebox-api[all]"

Container images (:mcp vs :agent)

One multi-stage docker/Dockerfile builds two right-sized images, selected by --target:

docker build --target mcp   -t knucklessg1/archivebox-api:mcp    docker/   # slim MCP server
docker build --target agent -t knucklessg1/archivebox-api:latest docker/   # full agent

docker/mcp.compose.yml runs the slim :mcp server; docker/agent.compose.yml runs the agent (:latest) with a co-located :mcp sidecar.

Knowledge-graph database (epistemic-graph)

The full agent ([agent] / :latest) embeds the epistemic-graph engine (pulled in transitively via agent-utilities[agent]). For production — or to share one knowledge graph across multiple agents — run epistemic-graph as its own database container and point the agent at it instead of embedding it. Deployment recipes (single-node + Raft HA), connection config, and the full database architecture (with diagrams) are documented in the epistemic-graph deployment guide. The slim [mcp] server does not require the database.

Documentation

The complete documentation is published as the official documentation site and is the recommended reference for installation, deployment, and day-to-day operation.

AGENTS.md is the canonical contributor/agent guidance.

Contribute

Contributions are welcome! Please ensure code quality by executing local checks before submitting pull requests:

• Format code using ruff format .

• Lint code using ruff check .

• Validate type-safety with mypy .

• Execute test suites using pytest

Available MCP Tools

The table below is auto-generated from the live server — do not edit by hand.

Condensed action-routed tools (default — MCP_TOOL_MODE=condensed)

Verbose 1:1 API-mapped tools (MCP_TOOL_MODE=verbose or both)

3 action-routed tool(s) (default) · 14 verbose 1:1 tool(s). Each is enabled unless its <DOMAIN>TOOL toggle is set false; MCP_TOOL_MODE selects the surface (condensed default · verbose 1:1 · both). Auto-generated — do not edit.

Additional Deployment Options

archivebox-api can also run as a local container (Docker / Podman / uv) or be consumed from a remote deployment. The Deployment guide has full, copy-paste mcp_config.json for all four transports — stdio, streamable-http, local container / uv, and remote URL:

• Local container / uv — launch the server from mcp_config.json via uvx, docker run, or podman run, or point at a local streamable-http container by url.

• Remote URL — connect to a server deployed behind Caddy at http://archivebox-mcp.arpa/mcp using the "url" key.

Deploy with agent-os-genesis

This package can be provisioned for you — skill-guided — by the agent-os-genesis universal skill (its single-package deploy mode): it picks your install method, seeds secrets to OpenBao/Vault (or .env), trusts your enterprise CA, registers the MCP server, and verifies it — the same machinery that stands up the whole Agent OS, narrowed to just this package. Ask your agent to "deploy archivebox-api with agent-os-genesis".

Secrets are read-existing + seeded via vault_sync — you are only prompted for what's missing.