Skip to main content
AllMCPs
BrowseBestCategoriesStackCompareToolsGuidesBlog
Log in Submit MCP

Stay in the loop

Get new MCP servers and top picks in your inbox.

AllMCPs

The open directory for discovering and installing Model Context Protocol servers.

AllMCPs on GitHub (opens in a new tab)
Launched onTiny Startupstinystartups.com
Explore
  • Browse servers
  • Best MCP servers
  • Categories
  • MCP clients
  • Agent prompts
  • Stack Builder
  • Compare servers
  • Random discovery New
  • Submit a server
  • Pricing & Boost Boost
Learn
  • Guides hub
  • What is MCP?
  • Install guide
  • Build an MCP server
  • Deploy an MCP server
  • Security guide
  • Troubleshooting
  • MCP for SEO & AEO
  • Protocol versioning
  • Blog & updates
Tools
  • All developer tools
  • Config generator
  • Config validator
  • Config auditor
  • MCP playground
  • Token calculator
  • OpenAPI β†’ MCP
  • Badge generator
For agents
  • REST API docs
  • Trust & traffic Live
  • Remote MCP server SSE β†— (opens in a new tab)
  • llms.txt β†— (opens in a new tab)
  • Catalog JSON β†— (opens in a new tab)
Company
  • About
  • Advertise Sponsor
  • Contact
  • GitHub β†— (opens in a new tab)
  • Terms
  • Privacy
AllMCPs VerifiedAllMCPs VerifiedFeatured on Nick LaunchesFeatured on Nick LaunchesLaunch Llama NewsletterLaunch Llama NewsletterVerified DR - allmcps.comVerified DR - allmcps.comFeatured on SaaSGrowFeatured on SaaSGrowFeatured on Twelve ToolsFeatured on Twelve ToolsFeatured on Saaspa.geFeatured on Saaspa.geFeatured on Findly.toolsFeatured on Findly.toolsFeatured on Startup FameFeatured on Startup FameFeatured on LaunchKiwiFeatured on LaunchKiwiFeatured on ScrollLaunchFeatured on ScrollLaunchFeatured on DailyPingsFeatured on DailyPingsFazier badgeFazier badgeFeatured on NewTool.siteFeatured on NewTool.siteFeatured on saasfame.comFeatured on saasfame.comDR Checker - Domain RatingDR Checker - Domain RatingListed on Turbo0Listed on Turbo0Launched on LaunchBoard - Product Launch PlatformLaunched on LaunchBoard - Product Launch PlatformList on SimilarlabsList on Similarlabshttps://codetrendy.comhttps://codetrendy.comListed on DevTool.ioFeatured on BuildlistFeatured on BuildlistLaunched on Tiny StartupsFeatured on ShowMeBestAIFeatured on ShowMeBestAIFind us on LaunchZoneFind us on LaunchZoneAllMCPs VerifiedAllMCPs VerifiedFeatured on Nick LaunchesFeatured on Nick LaunchesLaunch Llama NewsletterLaunch Llama NewsletterVerified DR - allmcps.comVerified DR - allmcps.comFeatured on SaaSGrowFeatured on SaaSGrowFeatured on Twelve ToolsFeatured on Twelve ToolsFeatured on Saaspa.geFeatured on Saaspa.geFeatured on Findly.toolsFeatured on Findly.toolsFeatured on Startup FameFeatured on Startup FameFeatured on LaunchKiwiFeatured on LaunchKiwiFeatured on ScrollLaunchFeatured on ScrollLaunchFeatured on DailyPingsFeatured on DailyPingsFazier badgeFazier badgeFeatured on NewTool.siteFeatured on NewTool.siteFeatured on saasfame.comFeatured on saasfame.comDR Checker - Domain RatingDR Checker - Domain RatingListed on Turbo0Listed on Turbo0Launched on LaunchBoard - Product Launch PlatformLaunched on LaunchBoard - Product Launch PlatformList on SimilarlabsList on Similarlabshttps://codetrendy.comhttps://codetrendy.comListed on DevTool.ioFeatured on BuildlistFeatured on BuildlistLaunched on Tiny StartupsFeatured on ShowMeBestAIFeatured on ShowMeBestAIFind us on LaunchZoneFind us on LaunchZone
Β© 2026 Jackalope Digital LLC. All rights reserved.
  1. Home
  2. πŸ‘¨β€πŸ’» Code Execution
  3. MCP Server
MCP Server logo
Health: ActiveRecent health check succeeded.Last checked 9/11/2026, 3:31:38 PM

MCP Server

User RatingsBe the first to rate and review this MCP server!
View Repository5 GitHub StarsTotal stargazers on GitHub for the source repository (5 stars).Visit Website
code-executionsandboxsecuritywasmaudit

MCP server providing sandboxed code execution and unified tool management with security and auditing features.

Quick Install

Automated & IDE Setup

Copy the AI prompt to install this server into Claude Code, Cursor, or another agent β€” or use 1-click editor setup below.

One-click editor setup isn’t available for this listing yet β€” we don’t have a confirmed install command, and we’d rather show nothing than point your editor at the wrong package or host. Follow the project’s own setup instructions, linked above.

Manual Client & Custom JSON ConfigExpand JSON β–Ύ
No confirmed setup config for this listing yet. We only publish a config block when the install details come from the project itself β€” its README, its docs, or a verified owner. We haven’t found those for telleroutlook/agentkit-js/mcp-server, and we’d rather show nothing than a guess you’d paste into your client. Follow the project’s own setup instructions for the current steps.
Install Directory Badge Claim listing AlternativesπŸ‘¨β€πŸ’» More in Code Execution

Overview

This MCP server consolidates multiple user-defined tools into a simplified interface with two main tools: execute code and search documentation. It enforces resource and security policies across three sandboxed execution kernels: in-process Node.js VM, WASM runtimes (QuickJS, Pyodide, Wasmtime), and remote microVMs (E2B, Cloudflare Sandbox). Use it when you need controlled, auditable, and isolated execution of agent-generated code with policy enforcement and evidence recording.

Use cases

β€’Execute agent-generated code securely in sandboxed environments
β€’Enforce runtime policies and resource limits on tool calls
β€’Record signed evidence of tool usage for auditing and compliance
β€’Share and sync semantic state between agents and UIs
β€’Vet and taint-track tool inputs and outputs for security

Key features

β€’Unified capability manifest enforcing allowed hosts, CPU, and memory limits
β€’Multiple sandbox kernels: Node.js VM, WASM (QuickJS, Pyodide, Wasmtime), remote microVMs
β€’Runtime firewall for vetting and policy enforcement of tool calls
β€’Signed evidence export (AEP) for auditing and compliance
β€’Reducer-backed shared state syncing between agent and UI
β€’Support for taint tracking and provenance of tool results

Capabilities & Tool Schemas

Inspect callable tools, capabilities, and parameters exposed to AI agents by MCP Server.

Extracted Tool Capabilities
Unified capability manifest enforcing allowed hosts, CPU, and memory limits
Multiple sandbox kernels: Node.js VM, WASM (QuickJS, Pyodide, Wasmtime), remote microVMs
Runtime firewall for vetting and policy enforcement of tool calls
Signed evidence export (AEP) for auditing and compliance
Reducer-backed shared state syncing between agent and UI
Support for taint tracking and provenance of tool results

Documentation Overview

wasmagent-js

npm version License: Apache-2.0 CI Quick Start Docs

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€” agent↔UI shared state


Start in 30 seconds

Pick your entry point:

GoalInstall
Protect tools β€” runtime firewall, policy enforcement, taint trackingnpm add @wasmagent/mcp-firewall
Record evidence β€” signed AEP records after every agent runnpm add @wasmagent/aep
Admit from traces β€” compliance scoring produces ComplianceEvalRecords for downstream trainingnpm add @wasmagent/aep @wasmagent/compliance
Sync state β€” reducer-backed agent↔UI shared state, agent reads projections + writes intentnpm add @wasmagent/core (/shared-state subpath)

Trust Pack β€” 30-minute end-to-end: docs/quickstarts/trust-pack-30min.md


Quickstart

Three paths β€” pick the one that fits your use case:

Path 1 β€” Protect: MCP runtime firewall

Wrap any MCP server: vet tools before execution, enforce policy per call, track taint across results.

Terminal
npm install @wasmagent/mcp-firewall
server.ts
import { evaluatePolicy, snapshotTool, taintObservation, vetTool } from "@wasmagent/mcp-firewall";

const entry = {
  name: "read_file",
  description: "Read a file from disk",
  inputSchema: { type: "object", properties: { path: { type: "string" } } },
};
const args = { path: "/tmp/report.txt" };
const consentRecords = [];

// Before calling a tool
const snap     = snapshotTool(entry, "my-server");   // hash descriptor at registration
const vetting  = vetTool(entry);                     // static scan: injection / exfil / rug-pull
const decision = evaluatePolicy(entry.name, args, vetting, consentRecords);

if (decision.decision === "deny")   throw new Error(`Blocked: ${decision.reasons.join("; ")}`);
if (decision.decision === "ask_user") {
  // surface consent UI, then call recordConsent(...)
}

// After receiving result
const rawResult = "example report contents";
const obs = taintObservation(entry.name, rawResult);  // boundary-tagged, safe to assemble into prompt

β†’ Security pack Β· OWASP Agentic Top 10 Β· Attack demos

Path 2 β€” Record: AEP evidence export

Emit a signed evidence record after every agent run β€” consumable by trace-pipeline for audit and training.

Terminal
npm install @wasmagent/aep
server.ts
import { AEPEmitter } from "@wasmagent/aep";

const emitter = new AEPEmitter({ run_id: "run-001", model_id: "claude-sonnet-4-6" });

// During the run β€” add tool call evidence
emitter.addAction({ tool_name: "bash", outcome: "pass", exit_code: 0 });

// At the end β€” emit the record
const record = emitter.build();
// record satisfies aep/v0.3 JSON Schema β€” ready for evomerge validate-aep

β†’ AEP schema Β· trace-pipeline 10-min tutorial

Path 3 β€” Execute: Sandboxed code execution

Run agent-generated code in an isolated WASM kernel β€” no host-process access.

Terminal
npm install @wasmagent/aisdk @wasmagent/kernel-quickjs
server.ts
import { sandboxedJsTool } from "@wasmagent/aisdk";
import { QuickJSKernel } from "@wasmagent/kernel-quickjs";

// Drop into any AI SDK / LangChain / OpenAI Agents setup
const codeTool = sandboxedJsTool({ kernel: new QuickJSKernel() });

β†’ Kernel comparison Β· Getting started

Path 4 β€” Sync: Human-agent shared state

Reducer-backed collaborative state where the LLM reads projections, dispatches semantic actions, and respects affordances β€” all through standard tools.

Terminal
npm install @wasmagent/core
server.ts
import { defineStateModel, SharedStateStore, stateTools } from "@wasmagent/core/shared-state";

// 1. One reducer, shared by both UI and agent.
const model = defineStateModel({
  initial: () => ({ page: "list", selectedId: null as string | null }),
  reduce: (s, a) => {
    if (a.type === "SELECT") return { ...s, page: "detail", selectedId: a.id };
    if (a.type === "BACK")   return { ...s, page: "list", selectedId: null };
    return s;
  },
  project: (s) => ({ page: s.page, selectedId: s.selectedId }),
  affordances: (s) => s.page === "list" ? ["SELECT"] : ["BACK"],
});

// 2. Server-side store keyed by session.
const store = new SharedStateStore(model);

// 3. Give the agent read_state + dispatch_action tools.
const tools = stateTools(store, "session-001");
// Pass `tools` to any ToolCallingAgent β€” the LLM reads state and dispatches intent.

The semantic action stream doubles as AEP evidence β€” every dispatch is a provenance-ready record (see #141 for the full confluence design).


πŸ“š Docs Β· Getting started Β· Kernels Β· OWASP governance Β· Security pack Β· Changelog


What is shipped vs alpha

WasmAgent uses a five-tier maturity scale to prevent "shipped" from becoming a vague claim:

TierMeaningSemver guaranteeProduction use
stablePublic API locked; breaking changes require major-version bumpYesYes
betaFunctional and used in production, but a specific limitation is documented (e.g. first-line filter only, contract still evolving)Minor/patch onlyYes, with caveats documented
alphaSchema versioned; fields may be added without a breaking-change bumpNoInformed use
demoDemonstration or example code; not hardened for productionNoNo
researchResearch-grade prototype; interfaces may change without noticeNoNo

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

PackageMaturityNotes
@wasmagent/corestablePublic API; semver guaranteed
@wasmagent/kernel-quickjsstable
@wasmagent/kernel-remotestable
@wasmagent/mcp-gatewaystablePublished 0.1.0; gateway composes all firewall layers
@wasmagent/mcp-firewallbetaFirst-line filter, not adversarial-grade β€” keyword bag + lightweight n-gram classifier; use defence-in-depth
@wasmagent/aepbetav0.2 signature contract (Ed25519) shipped; schema versioned
@wasmagent/otel-exporteralphaGENAI_SEMCONV, AEP↔OTel bridge
@wasmagent/aisdk / @wasmagent/mastra-sandboxalphaAPI stable, may add fields
@wasmagent/compliancealphaSchema versioned; may add fields without breaking
@wasmagent/mcp-policyalpha β€” privateNot yet published to npm
@wasmagent/mcp-attestationalpha β€” privateNot yet published to npm
@wasmagent/evals-runneralpha
@wasmagent/devtoolsalpha

WasmAgent Ecosystem

WasmAgent is a portable, governable agent runtime for safe code execution, verifiable rollouts, and post-training data loops.

RepoRole
wasmagent-js (this repo)Embedded Agent Runtime / WASM Kernel / policy / verifier / adapters
bscodeCloudflare flagship demo and deploy template for safe coding agents
trace-pipelinePublic datafactory and eval-trust backend for rollout data
text
Task β†’ Safe Runtime β†’ Verifiable Rollout β†’ Trajectory Export β†’ DPO/PPO Data β†’ Better Models

What makes wasmagent different

Three wedges where wasmagent stands apart from generic agent frameworks:

WedgeWhat it means
Sandboxed executionThree isolation tiers β€” VmKernel / WASM (QuickJSΒ·PyodideΒ·Wasmtime) / microVM β€” with a single CapabilityManifest and MCP runtime firewall across all
Runtime complianceTaskSpec β†’ ConstraintIR β†’ ComplianceEvalRecord β€” every run produces an auditable, cross-repo training contract, not just a log
Trace-to-training contractVerifiable rollout branching, objective scoring, DPO/PPO export β€” the loop from runtime evidence to training data is first-class, not an afterthought
Full feature axis table (10 axes vs. other JS agent frameworks)

Read the full README β†’View source on GitHub β†’

Related MCP Servers

View all in Code Execution View all alternatives
  • MCP Run Python logoMCP Run Python

    Run Python code in a secure sandbox via MCP tool calls

    πŸ‘¨β€πŸ’» Code Execution1 views
    Compare vs MCP Run Python β†’
  • MCP Server logoMCP Server

    Run untrusted Python/JavaScript code in WebAssembly sandboxes.

    πŸ‘¨β€πŸ’» Code Execution1 views
    Compare vs MCP Server β†’
  • MCP Server Js logoMCP Server Js

    Execute any LLM-generated code in a secure and scalable sandbox environment and create your own MCP tools using JavaScript or Python, with full support for NPM and PyPI packages

    πŸ‘¨β€πŸ’» Code Execution2 views
    Compare vs MCP Server Js β†’
  • MCP Js logoMCP Js

    A Javascript code execution sandbox that uses v8 to isolate code to run AI generated javascript locally without fear. Supports heap snapshotting for persistent sessions.

    πŸ‘¨β€πŸ’» Code Execution2 views
    Compare vs MCP Js β†’

Adoption & maintenance

Factual signals from GitHub, npm, and our automated checks β€” not a rating.

GitHub stars
5
Stargazers on the source repository.
Last commit
27d ago
Most recent push to the default branch.
Directory activity
2 views
Config copies, upvotes, and views on AllMCPs.

Reviews

No reviews yet β€” be the first to share how this listing worked for you.

Frequently Asked Questions about MCP Server

It supports in-process Node.js VM, WASM runtimes including QuickJS, Pyodide, Wasmtime, and remote microVMs like E2B and Cloudflare Sandbox.

AllMCPs Directory Badge

Full Badge Customizer

Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.

Badge Style:
Live Dynamic SVG PreviewMCP Server AllMCPs Directory Badge
Markdown (GitHub README)
[![AllMCPs](https://allmcps.com/api/badge/telleroutlook-agentkit-js-mcp-server?style=directory)](https://allmcps.com/mcp/telleroutlook-agentkit-js-mcp-server)
HTML Embed
<a href="https://allmcps.com/mcp/telleroutlook-agentkit-js-mcp-server"><img src="https://allmcps.com/api/badge/telleroutlook-agentkit-js-mcp-server?style=directory" alt="MCP Server on AllMCPs" /></a>

Technical Specs & Signals

CategoryπŸ‘¨β€πŸ’»Code Execution
PricingFree
More technical detailsExpand β–Ύ
AuthNo auth required
LicenseApache-2.0
Last updatedAug 15, 2026
3/4 checks healthy over the last 32d
Views2
Unique ViewsTotal visits recorded for this listing page on AllMCPs.
Installs0
Installs & Copy ActionsTotal times users copied install commands or configuration snippets for this server.
GitHub stars5
GitHub Star CountTotal stargazers on GitHub representing community popularity (5 stars).
Last commit27d ago
Last Repository CommitThe most recent commit or push recorded for this server's GitHub repository.Last commit on Aug 15, 2026
48Quality signal: Fair Β· 48/100How this signal is calculated β–Ύ
Server availabilityNot measured

Not scored for repo-hosted servers β€” we can't reach the running server, only its GitHub page. Hosted MCP endpoints are health-checked live.

Verified ownership10/20
Documentation & tools21/30
Adoption & activity5/15
Community engagement0/10

A guidance signal from public completeness & health data β€” not a user rating. New listings start lower and rise as they add docs, get verified, and grow adoption. Signals we can't observe for a listing are skipped, not counted against it.

β˜… FeaturedAllMCPs Server logo

AllMCPs Server

The official MCP server for AllMCPs.com - submit and manage tools directly from your AI. The open directory for MCP servers. Connect Claude, Cursor, Windsurf, and AI agents to databases, tools, files, and APIs. Explore 10,000+ servers. AllMCPs is the premier, open directory for discovering, evaluating, and installing Model Context Protocol (MCP) servers to equip AI agents and LLMs with real-world superpowers.

Explore Server β†’

Own this project?

This directory is pre-filled from public sources. Claim via GitHub README, site badge, or DNS TXT to unlock edit access and the Official badge β€” proof is checked automatically, then reviewed by our team.

Free dofollow backlink: add your website and place the AllMCPs badge on it β€” no claim needed. We detect it automatically and keep it verified as long as the badge stays live.

Claim & get free dofollow

Share & Embed

Add our SVG badge (dark/light directory styles) or embeddable widget to your site.

Explore more

More in πŸ‘¨β€πŸ’» Code Execution β†’Best MCP servers for Code Execution β†’Alternatives to MCP Server β†’Install in Claude DesktopInstall in CursorInstall in VS Code