1. Conduid
  2. Developer Tools
  3. Beddel
MCP server · Developer Tools

Beddel

MCP server: Beddel

Unclaimed last commit 7 months ago devtools
44Fair

Scored 4 months ago · breakdown

About Beddel

Beddel is an MCP server published by botanarede in the Developer Tools category: mCP server: Beddel. It has been installed 0 times through Conduid.

The repository has 6 stars and 0 forks, with the last commit 7 months ago. Six months or more without a commit doesn't mean the server is broken, but check the open issues (0) before depending on it in production.

Install

Install
npx beddel

This server has no ConduID identity, so agent calls to it are not receipted. Pin the version you install and review the source before granting it credentials.

Ask AI

Ask AI about Beddel

Powered by Claude · Grounded in docs

I know everything about Beddel. Ask me about installation, configuration, usage, or troubleshooting.

Security checks

  • ·README presentNot checked yet.
  • ·License declaredNot checked yet.
  • ·Tests presentNot checked yet.
  • ·Dependencies pinnedNot checked yet.
  • ·No dynamic code executionNot checked yet.
  • !Scoped permissionsDoesn't declare a permission scope. Assume it can do anything its process can.

README


Beddel is a Python SDK for declarative AI workflow execution. Define workflows in YAML, compose them from atomic primitives (llm, chat, guardrail, tool, call-agent, agent-exec), and let the engine handle branching, retry, reflection loops, parallel execution, and multi-provider LLM routing — all without boilerplate code.

Solution Kits extend the slim core with isolated adapters, tools, and integrations. Install only what you need.

Install

pip install "beddel[default]"    # batteries included: litellm + otel + fastapi + httpx

Or start minimal and add kits as needed:

pip install beddel                          # core only (3 deps: pydantic, pyyaml, click)
beddel kit install provider-litellm-kit     # add LLM provider support

Requires Python 3.11+.

Quick Example

# workflow.yaml
steps:
  - id: greet
    primitive: llm
    config:
      model: gemini/gemini-2.0-flash
      prompt: "Say hello and share a fun fact about $input.topic"
      temperature: 0.7
export GEMINI_API_KEY="your-key"
beddel run workflow.yaml -i topic=astronomy

Solution Kits

Each kit is a self-contained package with its own dependencies declared in kit.yaml. The install command resolves sources and handles pip dependencies automatically.

beddel kit install <kit-name>               # from this repository
beddel kit install ./my-custom-kit/         # from a local directory
beddel kit install github:org/repo/kits/x   # from any GitHub repo
beddel kit list                             # list installed kits

🔌 Providers

Kit Description Dependencies
provider-litellm-kit Multi-provider LLM adapter — 100+ providers via LiteLLM (OpenAI, Gemini, Anthropic, Bedrock, Ollama, and more) litellm

🤖 Agent Adapters

Kit Description Dependencies
agent-claude-kit Claude Agent SDK subprocess-based agent adapter claude-agent-sdk
agent-codex-kit Codex Docker-isolated agent adapter
agent-kiro-kit Kiro CLI subprocess-based agent adapter
agent-openclaw-kit OpenClaw Gateway HTTP API agent adapter httpx

📡 Protocols

Kit Description Dependencies
protocol-mcp-kit Model Context Protocol client (stdio + SSE transports) mcp, jsonschema

🔐 Auth

Kit Description Dependencies
auth-github-kit GitHub OAuth Device Flow credential management httpx

👁️ Observability

Kit Description Dependencies
observability-otel-kit OpenTelemetry tracing adapter — workflow, step, and primitive-level spans with token tracking opentelemetry-api
observability-langfuse-kit Langfuse tracing adapter — token usage, latency, and cost attribution langfuse

🌐 Serving

Kit Description Dependencies
serve-fastapi-kit FastAPI handler factory + SSE streaming — expose workflows as HTTP endpoints fastapi, sse-starlette
serve-mcp-kit Expose YAML workflows as MCP servers — any MCP-compatible agent can discover and execute them mcp

🛠️ Tools

Kit Description Dependencies
tools-file-kit File I/O tools (read, write) with path validation
tools-shell-kit Shell command execution via SafeSubprocessRunner
tools-http-kit HTTP request tool via httpx httpx
tools-gates-kit Validation gate tools (pytest, ruff, mypy)

📦 Development

Kit Description Dependencies
software-development-kit Development workflow tools — validation gates and epic creation

Creating Your Own Kit

A kit is a directory with a kit.yaml manifest:

name: my-custom-kit
version: "1.0.0"
description: "What this kit does"
author: "Your Name"

targets:
  python:
    module: "my_custom_kit"
    dependencies:
      - "some-package>=1.0"

Place your Python module under src/ in the kit directory, then install:

beddel kit install ./my-custom-kit/

Links

Stay in the Loop

We write about agent-native patterns, workflow design, and SDK development on Substack.

Subscribe on Substack

License

MIT

README mirrored from the source repository 4 months ago. The original is authoritative.

Questions

About Beddel

How do I install Beddel?

Run npx beddel, then add the server to your MCP client's configuration. Conduid has recorded 0 installs, so the command is known to work with current clients.

Is Beddel safe to use with an AI agent?

Its trust score is 44 out of 100 (fair). It passes 0 of 1 static security checks; the failures are listed above. It has no ConduID identity yet, so agent calls to it are not receipted.

Is Beddel still maintained?

The last commit was 7 months ago, with 0 open issues. That's long enough that you should check whether the maintainer is responding to issues before depending on it.