FRENES

Code execution · MCP server

Edict: MCP server, setup and security

Edict is an open-source MCP server published on GitHub that lets an AI agent emit JSON AST programs for verification and compilation to WASM. Its repository has 13 stars and its last commit is from October 17, 2026 and it is licensed under MIT.

Score
61/100
Adoption (stars) 11/40
Maintenance 30/30
Framework (licence, registry, official) 20/30
Actively maintainedSystem access

What Edict does

According to its repository: “Agent-oriented programming language: agents emit a JSON AST that the compiler validates, type- and effect-checks, verifies with Z3/SMT and compiles to WASM.”

The Model Context Protocol (MCP) is a standard plug between an AI agent and an outside service: once the server is connected, its tools show up in the agent, which decides when to call them. Edict is listed under Code execution, a category of 32 servers in the directory, where it ranks #26 by stars.

Topics declared by the repository: ai-agents, compiler, effect-system, formal-verification, json-ast, programming-language.

Installing and connecting Edict

Distribution modes declared in the official MCP registry:

  • npm package (Node.js, usually started with npx)

It works with any MCP-compatible client (Claude Desktop, Claude Code, Cursor, VS Code, Codex and most recent agents). You add one entry to the client's MCP configuration: server name, start command or URL, environment variables. Project language: TypeScript.

Security: what to check

Connecting an MCP server means installing software that talks straight to your agent: it runs with your rights and the model trusts its tool descriptions. The risk therefore depends on what it can touch and how far its code can be trusted.

Points found for Edict:

  • System access: the Code execution category gives the agent control over files, a terminal, code or a browser. A booby-trapped instruction in content the agent reads (prompt injection) can then turn into an action.

Good practice: grant only the rights needed (least privilege), require human approval for irreversible actions, and run the AI agent security check.

Project activity and maintenance

Created on February 24, 2026, the Sowiedu/Edict repository has 13 stars and 2 forks, with 0 open issues. It has more stars than 31% of the servers in the directory. It received changes this month. Version published in the registry: 1.9.2 (March 11, 2026).

Stars measure attention, not quality: a recent, heavily promoted project can collect them fast, while a useful but niche server will have few.

Container useContainer use : 4.1K4.1KMATLAB MCP ServerMATLAB MCP Server : 1.7K1.7KLLM SandboxLLM Sandbox : 1.1K1.1KTidewave PhoenixTidewave Phoenix : 858858Tidewave RailsTidewave Rails : 476476SuperserveSuperserve : 466466IPhone UseIPhone Use : 345345OrcaReplayOrcaReplay : 281281EdictEdict : 1313
GitHub stars of the most followed servers in the category (log scale); Edict in orange. Checked October 25, 2026.

Verdict

Edict is a reasonable choice; check the points below before connecting it.

Strengths

  • Active project: recent commit
  • Listed in the official MCP registry
  • Permissive licence (MIT)

Avoid if…

  • You cannot isolate the agent (sandbox, container)

Frequently asked questions

How do I install Edict?

Edict is distributed as npm package (Node.js, usually started with npx). Add it to your client's MCP configuration (Claude Desktop, Cursor, VS Code…) following the README of Sowiedu/Edict.

Is Edict free?

The code is published under the MIT licence and can be used free of charge.

Is Edict safe?

Points to watch: system access. Give it minimum rights and approve sensitive actions.

Is it an official server?

Nothing says so: it is a project published by Sowiedu on GitHub. Check who maintains it before giving it access.

What are the alternatives to Edict?

In the same category: Container use, LLM Sandbox, Tidewave Phoenix, and Superserve. Container use and LLM Sandbox score higher on our grid.

Related articles

Neutrality. No affiliate links. No vendor pays to be reviewed, rated or ranked. Reviews are directed by François Chollet, neutral and factual, and every data point is dated and sourced. How we score