WasmAgent MCP server β WASM-sandboxed code execution with capability manifests and Tasks API.
Copy the AI prompt to install this server into Claude Code, Cursor, or another agent β or use 1-click editor setup below.
π‘ Paste the JSON block into your client's configuration file under mcpServers, then restart the application.
WasmAgent adds a verifiable evidence layer to agent tool use: protect tool calls, record what happened, audit the result, and admit trusted traces into downstream systems.
Protect β Record β Audit β Admit Β· Sync β agentβUI shared state
Pick your entry point:
| Goal | Install |
|---|---|
| Protect tools β runtime firewall, policy enforcement, taint tracking | npm add @wasmagent/mcp-firewall |
| Record evidence β signed AEP records after every agent run | npm add @wasmagent/aep |
Admit from traces β compliance scoring produces ComplianceEvalRecords for downstream training | npm add @wasmagent/aep @wasmagent/compliance |
| Sync state β reducer-backed agentβUI shared state, agent reads projections + writes intent | npm add @wasmagent/core (/shared-state subpath) |
Trust Pack β 30-minute end-to-end: docs/quickstarts/trust-pack-30min.md
Three paths β pick the one that fits your use case:
Wrap any MCP server: vet tools before execution, enforce policy per call, track taint across results.
β Security pack Β· OWASP Agentic Top 10 Β· Attack demos
Emit a signed evidence record after every agent run β consumable by trace-pipeline for audit and training.
β AEP schema Β· trace-pipeline 10-min tutorial
Run agent-generated code in an isolated WASM kernel β no host-process access.
β Kernel comparison Β· Getting started
Reducer-backed collaborative state where the LLM reads projections, dispatches semantic actions, and respects affordances β all through standard tools.
The semantic action stream doubles as AEP evidence β every dispatch is a provenance-ready record (see #141 for the full confluence design).
π Docs Β· Getting started Β· Kernels Β· OWASP governance Β· Security pack Β· Changelog
WasmAgent uses a five-tier maturity scale to prevent "shipped" from becoming a vague claim:
| Tier | Meaning | Semver guarantee | Production use |
|---|---|---|---|
| stable | Public API locked; breaking changes require major-version bump | Yes | Yes |
| beta | Functional and used in production, but a specific limitation is documented (e.g. first-line filter only, contract still evolving) | Minor/patch only | Yes, with caveats documented |
| alpha | Schema versioned; fields may be added without a breaking-change bump | No | Informed use |
| demo | Demonstration or example code; not hardened for production | No | No |
| research | Research-grade prototype; interfaces may change without notice | No | No |
Packages not listed here (model adapters, UI cards, etc.) follow the same scale β see each package's README or package.json wasmagent.stability field.
| Package | Maturity | Notes |
|---|---|---|
@wasmagent/core | stable | Public API; semver guaranteed |
@wasmagent/kernel-quickjs | stable | |
@wasmagent/kernel-remote | stable | |
@wasmagent/mcp-gateway | stable | Published 0.1.0; gateway composes all firewall layers |
@wasmagent/mcp-firewall | beta | First-line filter, not adversarial-grade β keyword bag + lightweight n-gram classifier; use defence-in-depth |
@wasmagent/aep | beta | v0.2 signature contract (Ed25519) shipped; schema versioned |
@wasmagent/otel-exporter | alpha | GENAI_SEMCONV, AEPβOTel bridge |
@wasmagent/aisdk / @wasmagent/mastra-sandbox | alpha | API stable, may add fields |
@wasmagent/compliance | alpha | Schema versioned; may add fields without breaking |
@wasmagent/mcp-policy | alpha β private | Not yet published to npm |
@wasmagent/mcp-attestation | alpha β private | Not yet published to npm |
@wasmagent/evals-runner | alpha | |
@wasmagent/devtools | alpha |
WasmAgent is a portable, governable agent runtime for safe code execution, verifiable rollouts, and post-training data loops.
| Repo | Role |
|---|---|
| wasmagent-js (this repo) | Embedded Agent Runtime / WASM Kernel / policy / verifier / adapters |
| bscode | Cloudflare flagship demo and deploy template for safe coding agents |
| trace-pipeline | Public datafactory and eval-trust backend for rollout data |
Three wedges where wasmagent stands apart from generic agent frameworks:
| Wedge | What it means |
|---|---|
| Sandboxed execution | Three isolation tiers β VmKernel / WASM (QuickJSΒ·PyodideΒ·Wasmtime) / microVM β with a single CapabilityManifest and MCP runtime firewall across all |
| Runtime compliance | TaskSpec β ConstraintIR β ComplianceEvalRecord β every run produces an auditable, cross-repo training contract, not just a log |
| Trace-to-training contract | Verifiable rollout branching, objective scoring, DPO/PPO export β the loop from runtime evidence to training data is first-class, not an afterthought |
No reviews yet β be the first to share how this listing worked for you.
Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.
[](https://allmcps.com/mcp/mcp-server-163)<a href="https://allmcps.com/mcp/mcp-server-163"><img src="https://allmcps.com/api/badge/mcp-server-163?style=directory" alt="Wasmagent Js on AllMCPs" /></a>