Jilebi

$$$$$\ $$\ $$\ $$\ $$\ \__$$ |\__|$$ | $$ | \__| $$ |$$\ $$ | $$$$$$\ $$$$$$$\ $$\ $$ |$$ |$$ |$$ __$$\ $$ __$$\ $$ | $$\ $$ |$$ |$$ |$$$$$$$$ |$$ | $$ |$$ | $$ | $$ |$$ |$$ |$$ ____|$$ | $$ |$$ | \$$$$$$ |$$ |$$ |\$$$$$$$\ $$$$$$$ |$$ | \______/ \__|\__| \_______|\_______/ \__|

A powerful, plugin-based MCP (Model Context Protocol) server that extends AI assistants with custom tools, resources, and prompts.

- Overview
- Download
- Installation

- Windows
- Linux
- macOS

curl -fsSL https://mcp.jilebi.ai/install.sh | bash

wget -qO- https://mcp.jilebi.ai/install.sh | bash

irm https://mcp.jilebi.ai/install.ps1 | iex

Invoke-RestMethod https://mcp.jilebi.ai/install.ps1 | Invoke-Expression

curl -fsSL https://mcp.jilebi.ai/uninstall.sh | bash

wget -qO- https://mcp.jilebi.ai/uninstall.sh | bash

irm https://mcp.jilebi.ai/uninstall.ps1 | iex

# Skip confirmation prompts irm https://mcp.jilebi.ai/uninstall.ps1 -OutFile uninstall.ps1; .\uninstall.ps1 -Force # Keep plugins and data irm https://mcp.jilebi.ai/uninstall.ps1 -OutFile uninstall.ps1; .\uninstall.ps1 -KeepData

# 1. Unzip the downloaded file to your desired location # 2. Install recommended plugins .\jilebi.exe plugins add memory .\jilebi.exe plugins add sequential-thinking # 3. Start the MCP server .\jilebi.exe stdio

# 1. Unzip the downloaded file to your desired location # 2. Grant execution access chmod +x jilebi # 3. Install recommended plugins ./jilebi plugins add memory ./jilebi plugins add sequential-thinking # 4. Start the MCP server ./jilebi stdio

# 1. Unzip the downloaded file to your desired location # 2. Grant execution access chmod +x jilebi # 3. Remove quarantine attribute (required for unverified developers) xattr -d com.apple.quarantine /path/to/jilebi # 4. Install xz dependency brew install xz # 5. Install recommended plugins ./jilebi plugins add memory ./jilebi plugins add sequential-thinking # 6. Start the MCP server ./jilebi stdio

Find more plugins atgithub.com/datron/jilebi-plugins

{ "mcpServers": { "jilebi": { "command": "jilebi", "args": ["stdio"], "env": {} } } }

{ "mcpServers": { "jilebi": { "command": "jilebi", "args": ["stdio"], "env": {} } } }

{ "mcpServers": { "jilebi": { "command": "jilebi", "args": ["stdio"], "env": {} } } }

{ "servers": { "jilebi": { "type": "stdio", "command": "jilebi", "args": ["stdio"] } } }

{ "context_servers": { "jilebi": { "command": "jilebi", "args": ["stdio"], "enabled": true, "source": "custom", "env": {} } } }

[mcp_servers.jilebi] command = "jilebi" args = ["stdio"]

{ "$schema": "https://opencode.ai/config.json", "mcp": { "jilebi": { "type": "local", "command": ["jilebi", "stdio"], "enabled": true, "environment": {} } } }

Plugins extend Jilebi with custom functionality through three main components:

# Install a plugin jilebi plugins add <plugin-name> # Create a new plugin jilebi plugins create # Setup/reconfigure a plugin jilebi plugins setup <plugin-name> # View plugin logs jilebi plugins log <plugin-id>

Follow the prompts to bootstrap a new plugin project.

Plugins are defined using a TOML manifest file. Here is an example structure:

# Metadata name = "my-plugin" version = "1.0.0" homepage = "github.com/user/my-plugin" creator = "Your Name" contact = "you@example.com" # Environment Variables [env] API_URL = { schema = { type = "string" }, default = "https://api.example.com" } # Secrets (no defaults allowed) [secrets] API_KEY = { schema = { type = "string" } } # Tools [tools.my-tool] name = "my-tool" description = "Description of what this tool does" input_schema = { type = "object", properties = { param = { type = "string" } }, required = ["param"] } function = "my_tool_function" [tools.my-tool.permissions] hosts = ["https://api.example.com"] # Resources [resources.my-resource] name = "my-resource" description = "Description of this resource" mime_type = "application/json" function = "get_resource" # Prompts [prompts.my-prompt] name = "my-prompt" description = "A helpful prompt template" arguments = [ { name = "topic", description = "The topic to discuss", required = true } ] messages = [ { role = "user", content = { type = "text", content = "Tell me about {{topic}}" } } ]

Plugins can request the following permissions:

Use"user_defined"to prompt the user for a custom value during setup.

- setState(env, key, value)- Persist data across sessions
- getState(env, key)- Retrieve persisted data
- deleteState(env, key)- Remove persisted data

- Directory operations:mkdir,readDir
- File operations:readFile,writeFile,readTextFile,writeTextFile
- File manipulation:stat,copyFile,rename,remove
- Temporary files:makeTempDir,makeTempFile
- And more...

# View Jilebi server logs jilebi log # View plugin-specific logs jilebi plugins log <plugin-id>

console.log("Info message"); console.warn("Warning message"); console.error("Error message"); console.debug("Debug message");

Built with the Model Context Protocol (MCP) specification version 2025-03-26

Remote MCP server (Streamable HTTP) at https://mcp.agenticrail.nz/ — deterministic step-order enforcement for AI agents. evaluate_step returns ALLOW or DENY before a step runs; verify_receipt proves a sequence's Ed25519-signed, hash-chained receipt chain is intact. No auth required: omit the bearer token and calls run on the public demo key. That first clause matters — the form has no "remote/hosted" field, and putting the endpoint in the description is the convention on that list ("Fully REMOTE! Just use…"). The rest mirrors your own server card verbatim, so the listing and the card can't drift.

AMS – Deterministic Agent Pipeline with A2A‑style Orchestration and Cryptographic Audit

Universal registry for 20,000+ MCP servers and agent skills with A/B/C/F security grading, CLI installer (npx loaditout add), verified publisher badges, and curated packs.

Wrap your local MCP servers to check every tool call against policy and live state before it runs - allow, block, or request a refresh, with a reason the agent can act on.

A Windows and MacOS app to manage local and remote MCP servers from a single interface with secure access control and logging.

Context Minifier & State Guard — Local-first MCP middleware proxy that reduces token waste by 61%, prevents context rot, and adds security hardening

A local execution vault for AI Agents: providing encrypted key authorization, encrypted task‑chain execution, and controlled external execution permissions. It preserves the high‑efficiency execution capability of AI while protecting user data and cognitive assets — putting a real harness on AI (AI Harness).

17 developer tools for AI agents — JSON, JWT, regex with code gen, cron from English, secrets scanner, batch ops. 7 free, 10 Pro ($7).

A sandboxed, agentic workspace providing secure filesystem, bash, and uv-powered Python execution.

Free public MCP for AI agents — 193 tools, 44 workflows. No API key. JSON Schema, semver, secrets scan, OpenAPI, cron, hash, regex.