The MCP directory / Open to explore
MCP server directory.
Find your next tool.
Search 3,974 indexed servers from the official MCP Registry and selected vendor documentation. Find remote endpoints and local packages, inspect the publisher’s setup details, then connect in your AI client.
Where will your next task take you?
Free discovery · no account · no API key
Let your agent do the finding.
Read https://toolcargo.com/agents.txt, then find the MCP servers I need and help me connect them. Ask me what I want to do first.Or add https://toolcargo.com/mcp as a Streamable HTTP MCP server. Discovery is free and needs no account.
Compare task fit, publisher, permissions and a small acceptance test with the MCP server selection guide.
Connect directly to official MCP servers
Vendor setup guides for your existing accounts. These connections run with the vendor; ToolCargo does not host them or supply their credentials.
Browse the remote MCP server directory →
Not sure which connection to choose? Read local vs remote MCP servers. Building a discovery workflow? See the MCP server search API reference.
browser-devtools-mcp
Close detailsPlaywright browser & Node.js MCP. ARIA refs, screenshots, ref-based interactions.
Directory identity: io.github.serkan-ozal/browser-devtools-mcp · Version: 0.9.1
{
"remotes": [
{
"type": "streamable-http",
"url": "https://{your_mcp_server_host}/mcp",
"variables": {
"your_mcp_server_host": {
"description": "Your self-hosted MCP server host (host:port, without scheme).",
"isRequired": true
}
}
}
],
"packages": [
{
"registryType": "npm",
"registryBaseUrl": "https://registry.npmjs.org",
"identifier": "browser-devtools-mcp",
"version": "0.9.1",
"transport": {
"type": "stdio"
},
"environmentVariables": [
{
"description": "Platform: browser (default) or node for Node.js backend debugging.",
"format": "string",
"name": "PLATFORM"
},
{
"description": "Port for HTTP transport.",
"format": "number",
"name": "PORT"
},
{
"description": "Idle session timeout (seconds).",
"format": "number",
"name": "SESSION_IDLE_SECONDS"
},
{
"description": "Interval for checking idle sessions (seconds).",
"format": "number",
"name": "SESSION_IDLE_CHECK_SECONDS"
},
{
"description": "Close session when socket closes.",
"format": "boolean",
"name": "SESSION_CLOSE_ON_SOCKET_CLOSE"
},
{
"description": "Maximum console messages to buffer.",
"format": "number",
"name": "CONSOLE_MESSAGES_BUFFER_SIZE"
},
{
"description": "Maximum HTTP requests to buffer.",
"format": "number",
"name": "HTTP_REQUESTS_BUFFER_SIZE"
},
{
"description": "When true, include server instructions in MCP server info (browser platform). Default: true.",
"format": "boolean",
"name": "BROWSER_SERVER_INSTRUCTIONS_ENABLE"
},
{
"description": "When true, include UI_DEBUGGING_POLICY in server policies (browser platform). Default: false.",
"format": "boolean",
"name": "BROWSER_POLICY_UI_DEBUGGING_ENABLE"
},
{
"description": "Run browser in headless mode.",
"format": "boolean",
"name": "BROWSER_HEADLESS_ENABLE"
},
{
"description": "Use persistent browser context (preserves cookies, localStorage, extensions).",
"format": "boolean",
"name": "BROWSER_PERSISTENT_ENABLE"
},
{
"description": "CDP attach: http(s) root or ws(s) URL. Resolves via /json/version, /json/list, or ws /devtools/browser (Chrome 136+). Mutually exclusive with BROWSER_PERSISTENT_ENABLE.",
"format": "string",
"name": "BROWSER_CDP_ENDPOINT_URL"
},
{
"description": "When true and no BROWSER_CDP_ENDPOINT_URL: probe 127.0.0.1:9222 then :9229 for CDP. Else use BROWSER_CDP_ENDPOINT_URL or default http://127.0.0.1:9222.",
"format": "boolean",
"name": "BROWSER_CDP_ENABLE"
},
{
"description": "On loopback CDP failure, if Chrome is running, open chrome://inspect/#remote-debugging. Default true. Set false to disable.",
"format": "boolean",
"name": "BROWSER_CDP_OPEN_INSPECT"
},
{
"description": "Directory for persistent browser context user data.",
"format": "string",
"name": "BROWSER_PERSISTENT_USER_DATA_DIR"
},
{
"description": "Use system-installed Chrome browser instead of Playwright's bundled browser.",
"format": "boolean",
"name": "BROWSER_USE_INSTALLED_ON_SYSTEM"
},
{
"description": "Custom browser executable path.",
"format": "string",
"name": "BROWSER_EXECUTABLE_PATH"
},
{
"description": "When false, launches Chromium with --no-sandbox. Required for Docker/Lambda/CI.",
"format": "boolean",
"name": "BROWSER_CHROMIUM_SANDBOX"
},
{
"description": "Extra Chromium launch args (comma-separated).",
"format": "string",
"name": "BROWSER_LAUNCH_ARGS"
},
{
"description": "Comma-separated list of allowed hostnames. When set, all requests to non-matching hosts are aborted. Subdomains match automatically.",
"format": "string",
"name": "BROWSER_ALLOWED_DOMAINS"
},
{
"description": "Browser locale (e.g., \"en-US\", \"tr-TR\").",
"format": "string",
"name": "BROWSER_LOCALE"
},
{
"description": "Enable OpenTelemetry integration.",
"format": "boolean",
"name": "OTEL_ENABLE"
},
{
"description": "OpenTelemetry service name.",
"format": "string",
"name": "OTEL_SERVICE_NAME"
},
{
"description": "OpenTelemetry service version.",
"format": "string",
"name": "OTEL_SERVICE_VERSION"
},
{
"description": "Directory containing OpenTelemetry bundle files.",
"format": "string",
"name": "OTEL_ASSETS_DIR"
},
{
"description": "User interaction events to instrument (comma-separated, e.g., \"click,submit\").",
"format": "string",
"name": "OTEL_INSTRUMENTATION_USER_INTERACTION_EVENTS"
},
{
"description": "OpenTelemetry exporter type: \"otlp/http\", \"console\", or \"none\".",
"format": "string",
"name": "OTEL_EXPORTER_TYPE"
},
{
"description": "OpenTelemetry collector base URL (e.g., \"http://localhost:4318\").",
"format": "string",
"name": "OTEL_EXPORTER_HTTP_URL"
},
{
"description": "OpenTelemetry exporter HTTP headers (comma-separated key=value pairs).",
"format": "string",
"isSecret": true,
"name": "OTEL_EXPORTER_HTTP_HEADERS"
},
{
"description": "AWS region for Bedrock usage.",
"format": "string",
"name": "AWS_REGION"
},
{
"description": "AWS profile name for Bedrock usage.",
"format": "string",
"name": "AWS_PROFILE"
},
{
"description": "Enable Amazon Bedrock usage.",
"format": "boolean",
"name": "AMAZON_BEDROCK_ENABLE"
},
{
"description": "Amazon Bedrock image embedding model ID.",
"format": "string",
"name": "AMAZON_BEDROCK_IMAGE_EMBED_MODEL_ID"
},
{
"description": "Amazon Bedrock text embedding model ID.",
"format": "string",
"name": "AMAZON_BEDROCK_TEXT_EMBED_MODEL_ID"
},
{
"description": "Amazon Bedrock vision model ID.",
"format": "string",
"name": "AMAZON_BEDROCK_VISION_MODEL_ID"
},
{
"description": "Figma API access token for design comparison.",
"format": "string",
"isSecret": true,
"name": "FIGMA_ACCESS_TOKEN"
},
{
"description": "Figma API base URL.",
"format": "string",
"name": "FIGMA_API_BASE_URL"
},
{
"description": "Daemon mode port (CLI).",
"format": "number",
"name": "DAEMON_PORT"
},
{
"description": "Daemon mode idle session timeout (seconds).",
"format": "number",
"name": "DAEMON_SESSION_IDLE_SECONDS"
},
{
"description": "Daemon mode idle session check interval (seconds).",
"format": "number",
"name": "DAEMON_SESSION_IDLE_CHECK_SECONDS"
},
{
"description": "When true, include server instructions in MCP server info (node platform). Default: true.",
"format": "boolean",
"name": "NODE_SERVER_INSTRUCTIONS_ENABLE"
},
{
"description": "When true, include NODE_DEBUGGING_POLICY in server policies (node platform). Default: false.",
"format": "boolean",
"name": "NODE_POLICY_DEBUGGING_ENABLE"
},
{
"description": "Inspector host for debug_connect when MCP runs in Docker (e.g. host.docker.internal). Default: 127.0.0.1.",
"format": "string",
"name": "NODE_INSPECTOR_HOST"
},
{
"description": "When true, omit tool output schema from MCP tool registration (can reduce token usage for some clients).",
"format": "boolean",
"name": "TOOL_OUTPUT_SCHEMA_DISABLE"
},
{
"description": "Comma-separated tool domains to enable (e.g. navigation,interaction,a11y,scenario). Unset = all tools. Browser: a11y, content, debug, figma, interaction, navigation, o11y, react, scenario, run, stub, sync. Node: debug, run.",
"format": "string",
"name": "AVAILABLE_TOOL_DOMAINS"
},
{
"description": "Working directory for project-level config (.browser-devtools-mcp/). Default: process.cwd().",
"format": "string",
"name": "WORKING_DIR"
},
{
"description": "Search strategy: SIMPLE (default, minisearch + stemmer) or FTS5 (better-sqlite3, optional dep).",
"format": "string",
"name": "SEARCH_STRATEGY"
},
{
"description": "Override SEARCH_STRATEGY for scenario search only.",
"format": "string",
"name": "SCENARIO_SEARCH_STRATEGY"
}
]
}
]
}Remote URLs go into your client's MCP settings. Local packages need a compatible runtime. Check required headers, environment variables, permissions and provider costs before setup.
Publisher repository ↗3,974 results
Index updated 2026-10-02
- Local packageThird-party
BrowserMesh
io.github.scrollDynasty/browsermesh
Isolated multi-session Chromium runtime for external MCP clients over stdio.
View connection details → - Local packageThird-party
Builderforce Memory
io.github.SeanHogg/builderforce-memory
Token-saving persistent memory for AI agents: recall durable facts instead of re-reading files.
View connection details → - Local packageThird-party
Evergences Shared Memory
io.github.seanmeverett/shared-memory
Public source-linked memories for AI agents: search, read, cite, reply, and share findings.
View connection details → - Local packageThird-party
sendblue-browser-mcp
io.github.sendblue-api/sendblue-browser-mcp
Drive a stealth-patched Chromium daemon: navigate, screenshot, eval JS, attach over CDP.
View connection details → - Remote URLLocal packageThird-party
browser-devtools-mcp
io.github.serkan-ozal/browser-devtools-mcp
Playwright browser & Node.js MCP. ARIA refs, screenshots, ref-based interactions.
View connection details → - Local packageThird-party
Amazon Web Services MCP
io.github.Servosity/aws-billing-mcp
Get a non-expert from zero to a Slack-delivered, plain-English, waste-flagged AWS bill breakdown
View connection details → - Local packageThird-party
memory
io.github.shackleai/memory
Persistent memory for AI coding tools. 11 tools for any MCP-compatible AI tool.
View connection details → - Local packageThird-party
memory
io.github.sharedmemoryai/memory
Persistent memory for AI agents. Remember, recall, and explore a shared knowledge graph.
View connection details → - Local packageThird-party
Google AI Search MCP
io.github.shariqriazz/google-ai-search-mcp
Google AI search and documentation tools for MCP clients using Vertex AI or the Gemini API.
View connection details → - Remote URLThird-party
Swellmeter: Google Trends Scraper & API for AI Agents
io.github.shawmena-dotcom/google-trends
Google Trends for agents: trend verdict, stats, rising queries, regions, trending now.
View connection details → - Local packageThird-party
notion-mcp
io.github.shck-dev/notion-mcp
Notion MCP server — search, export, and import pages as markdown
View connection details → - Local packageThird-party
Slack Explorer MCP
io.github.shibayu36/slack-explorer-mcp
MCP server specialized in retrieving information from Slack messages and threads
View connection details → - Remote URLThird-party
Browser Proof
io.github.shin1219-eng/browser-proof
Evidence-backed web verification for agents with deterministic JSON, text evidence, and screenshots.
View connection details → - Local packageThird-party
SMRITI Memory
io.github.shivamtyagi18/smriti-memory
Neuro-inspired long-term memory for AI agents with semantic graph and consolidation.
View connection details → - Local packageThird-party
live-memory
io.github.shofer-dev/live-memory
Persistent, read-only codebase memory for Claude Code; ask it instead of re-reading files.
View connection details → - Remote URLThird-party
browser-mcp
io.github.Shreyas-Profile/browser-mcp
Hosted real Google Chrome MCP with per-user persistent state. Navigate, click, type, screenshot.
View connection details → - Remote URLLocal packageThird-party
Dados Abertos Senado BR MCP
io.github.SidneyBissoli/senado-br-mcp-cloudflare
MCP server for Brazilian Federal Senate open data (legislative, administrative, e-Cidadania).
View connection details → - Local packageThird-party
Public Browser
io.github.Silbercue/public-browser
Chrome over CDP for AI agents. Blind benchmark vs agent-browser: -33% tokens, -33% cost, -32% time
View connection details → - Local packageThird-party
Memory Engine MCP
io.github.SimoneB79/memory-engine-mcp
Local-first graph memory for AI assistants with SQLite, semantic search, and MCP tools.
View connection details → - Local packageThird-party
lightning-memory
io.github.singularityjason/lightning-memory
Decentralized agent memory for the Lightning economy. Nostr identity, L402 payments.
View connection details → - Local packageThird-party
cogmemory-mcp
io.github.skylarng89/cogmemory-mcp
CogMemory MCP Server — Unified context subsystems for AI coding agents
View connection details → - Local packageThird-party
M3 Memory
io.github.skynetcmd/m3-memory
Local-first memory — 100+ tools, 99.2% LongMemEval-S retrieval@10, hybrid search, GDPR, no cloud.
View connection details → - Local packageThird-party
SMRITI Memory
io.github.smriti-memcore/smriti-memory
Neuro-inspired long-term memory for AI agents with semantic graph and consolidation.
View connection details → - Local packageThird-party
memorymesh
io.github.sparkvibe-io/memorymesh
Persistent, zero-dependency AI memory using SQLite. Local-first, cross-tool portable.
View connection details →
This directory combines dated registry listings and selected vendor-documentation entries. Documentation checks are not live account or client verification. Third-party servers run with their own providers, credentials and pricing. ToolCargo discovery supplies setup metadata; it does not run their tools. Explore ToolCargo's hosted connectors.