Soma MCP Server
Provides C++ code verification by executing tests in a sandbox and issuing signed certificates, and can generate verified C++ code.
Supports verifying JavaScript code by running it against tests in a sandbox with signed verdicts, and generating certified JavaScript code for tasks.
Supports PHP code verification via sandboxed test execution with signed verdicts, and generation of certified PHP code.
Allows execution-verified testing for Python: run Python code against tests in an isolated sandbox, get PASS/FAIL verdicts with signed certificates, and generate verified Python code from prompts.
Enables Ruby code verification through sandboxed test execution with signed certificates, and can generate verified Ruby code from task descriptions.
Allows Rust code to be verified by running it against tests in an isolated sandbox, outputting signed certificates, and supports generating verified Rust code.
Provides test-execution verification for TypeScript code, including sandboxed execution and signed certificates, as well as generation of verified TypeScript code.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Soma MCP Server Generate verified Python code for a function that returns the larger of two numbers."
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Soma MCP Server
Give your AI agent the one thing it can't do for itself: actually run code against tests and prove it passed.
Soma is an execution-verified code service. This MCP server exposes two tools:
soma_verify_code— run candidate code against tests inside an isolated sandbox; get a PASS/FAIL verdict plus a signed, offline-checkable certificate (Ed25519). Use it to independently confirm code works before trusting it.soma_generate_verified_code— ask Soma to write code for a task; when the task is verifiable, the returned code has already been executed against derived tests, with a certificate attached.
15+ languages are supported for verification (Python, JavaScript/TypeScript, Go, C/C++, Java, Rust, Ruby, PHP, Bash, and more).
Install
Requires Node.js 18+. Runs over stdio.
Add to your MCP client config (Claude Desktop, Cursor, etc.):
{
"mcpServers": {
"soma": {
"command": "npx",
"args": ["-y", "soma-verify-mcp"],
"env": {
"SOMA_API_KEY": "YOUR_SOMA_KEY"
}
}
}
}Claude Desktop:
Settings → Developer → Edit Config, add the block above, restart.Cursor:
Settings → MCP → Add, or drop the same block in~/.cursor/mcp.json.
Related MCP server: OmniBridge MCP Server
Configuration
Env var | Required | Default | Purpose |
| yes | — | Your Soma API key. |
| no |
| Soma API base URL. |
| no |
| Per-request timeout. |
Get a free preview key: contact centrum.arvind@gmail.com (free tier during the preview).
Tools
soma_verify_code
Run code against tests and return a signed verdict.
language(string) — e.g.python,javascript,go,rust.code(string) — the complete source to verify.tests(array) — one of:function mode (default):
[{ "input": [arg1, arg2], "expected": value }]plusentrypoint(the function name).stdio mode: set
mode: "stdio"and[{ "stdin": "...", "expected_stdout": "..." }]; no entrypoint.
entrypoint(string, optional) — function name for function mode.mode("function"|"stdio", optional).
Returns: verdict, tests_passed, tests_total, and a signature / public_key / sig_alg you can check offline.
soma_generate_verified_code
Get code for a task, executed against derived tests before it's returned.
prompt(string) — the coding task. Include concrete input/output examples (e.g.>>> f(2) == 4) so the result is verifiable rather than best-effort.max_tokens(int, optional, default 1500).
Returns: the code, certified (bool), and a certificate (verdict, tests_passed, tests_total) when verification passed. If a task isn't verifiable, output is returned uncertified and clearly labeled — never a false "verified".
What the certificate means
A certificate attests that the listed tests passed inside an isolated sandbox at generation time. It is signed (Ed25519) and checkable offline against the returned public key. It is not a warranty of fitness for any purpose — review output before production use.
Privacy
No training on your prompts. See the Soma Privacy & Data Policy at ${SOMA_BASE_URL}/privacy.
License
MIT.
Available Tools
2 toolssoma_generate_verified_codeGenerate execution-verified codeARead-only
Ask Soma to write code for a task. When the task is verifiable, the returned code has been executed against derived tests in an isolated sandbox before it is returned, and a certificate (verdict + tests passed) is attached. Include concrete examples in the prompt (e.g. doctest-style '>>> f(2) == 4') to make the result verifiable rather than best-effort.
Inputs: prompt (required), max_tokens.
soma_verify_codeVerify code against tests (signed certificate)ARead-onlyIdempotent
Run candidate code against tests inside an isolated sandbox and return a PASS/FAIL verdict with a signed, offline-checkable certificate (Ed25519). Use this to independently confirm that code actually works before trusting it.
Two test shapes:
function mode (default): tests = [{"input": [arg1, arg2], "expected": value}] and provide 'entrypoint' (the function name).
stdio mode: set mode='stdio' and tests = [{"stdin": "...", "expected_stdout": "..."}]; no entrypoint needed.
Supported languages include python, javascript, typescript, go, c, cpp, java, rust, ruby, php, bash and more.
Inputs: code (required), tests (required), language (required), mode, +1 more.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 2 tools
The two tools have clearly distinct purposes: one verifies provided code, the other generates code with verification. There is no overlap or confusion between them.
Both tools follow the identical pattern of 'soma_' prefix plus a verb_noun structure: verify_code and generate_verified_code. Naming is uniform and predictable.
With only 2 tools, the server is minimal but focused on a narrow purpose. While the count feels thin for a general toolkit, it is reasonable for a specialized verification service. It sits at the borderline.
The server covers the core workflows of code verification and generation with verification. Minor gaps exist, such as no ability to fetch or check certificate details after generation, but the primary lifecycle is covered.
Maintenance
Related MCP Connectors
Hosted Python sandbox for package runtime verification: pip install and usable-import evidence.
Execute code in 8 languages (Python, JS, TS, Go, Java, C++, C, Bash) in gVisor sandboxes.
Execution platform for AI agents on Firecracker microVMs in the EU. Interactive Linux sandboxes with root, templates for Python, Node.js, Go, Rust and a headless browser, public HTTPS URLs. Background jobs that outlive the connection, batches of up to 1,000 jobs with dependencies, hard cost caps reserved up front, execution receipts with SHA-256, log digests that fit the context. IPv4, dual-stack or IPv6-only with its own public address, allowlists or no network. WASI runtime for small tasks. Idle sandboxes sleep and keep their files. Also REST API, Python SDK and LangChain.
Signed sandbox verdicts on any artifact, plus an agent marketplace. No key, no signup, no payment.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceEnables secure cloud-based execution of code across 14+ programming languages within a sandboxed environment. It supports file management, standard input/output handling, and automatic generation of visual artifacts like plots and charts.MIT
- AlicenseNot gradedqualityDmaintenanceProvides isolated sandbox environments for AI agents to execute code securely, generating signed receipts for every execution to ensure auditability and trust.14 npm6MIT
- AlicenseAqualityDmaintenanceProvides an isolated workspace for testing candidate code, runs tests, and returns deterministic pass/fail verdicts. Enables automated grading of software engineering solutions by ensuring reproducible test runs.5MIT
- AlicenseAqualityDmaintenanceProvides structured, sandboxed test and lint feedback for coding agents, returning compact typed verdicts with failure fingerprints instead of raw runner output. It enables impact-selected test execution in isolated containers, distinguishing pre-existing failures from regressions.4Apache 2.0