Crawler Summary

mcp-client answer-first brief

OpenClaw agent: mcp-client mcp-client A React-based web interface for interacting with the TRON blockchain through a **ReAct (Reasoning + Acting) AI agent**. Connects to an MCP server via SSE, supports **7 LLM providers** with runtime switching, and includes **client-side wallet integration** for signing and broadcasting transactions. Architecture Features AI Agent - **ReAct loop** — multi-step reasoning with tool calling - **7 LLM providers** Published capability contract available. No trust telemetry is available yet. Last updated 2/24/2026.

Freshness

Last checked 2/22/2026

Best For

Contract is available with explicit auth and schema references.

Not Ideal For

mcp-client is not ideal for teams that need stronger public trust telemetry, lower setup complexity, or more explicit contract coverage before production rollout.

Evidence Sources Checked

editorial-content, capability-contract, runtime-metrics, public facts pack

Claim this agent
Agent DossierGitHubSafety: 98/100

mcp-client

OpenClaw agent: mcp-client mcp-client A React-based web interface for interacting with the TRON blockchain through a **ReAct (Reasoning + Acting) AI agent**. Connects to an MCP server via SSE, supports **7 LLM providers** with runtime switching, and includes **client-side wallet integration** for signing and broadcasting transactions. Architecture Features AI Agent - **ReAct loop** — multi-step reasoning with tool calling - **7 LLM providers**

MCPverified

Public facts

6

Change events

1

Artifacts

0

Freshness

Feb 22, 2026

Verifiededitorial-content1 verified compatibility signal

Published capability contract available. No trust telemetry is available yet. Last updated 2/24/2026.

Schema refs publishedTrust evidence available

Trust score

Unknown

Compatibility

MCP

Freshness

Feb 22, 2026

Vendor

Tonylau00

Artifacts

0

Benchmarks

0

Last release

0.0.0

Executive Summary

Key links, install path, and a quick operational read before the deeper crawl record.

Verifiededitorial-content

Summary

Published capability contract available. No trust telemetry is available yet. Last updated 2/24/2026.

Setup snapshot

git clone https://github.com/TonyLau00/mcp-client.git
  1. 1

    Setup complexity is MEDIUM. Standard integration tests and API key provisioning are required before connecting this to production workloads.

  2. 2

    Final validation: Expose the agent to a mock request payload inside a sandbox and trace the network egress before allowing access to real customer data.

Evidence Ledger

Everything public we have scraped or crawled about this agent, grouped by evidence type with provenance.

Verifiededitorial-content
Vendor (1)

Vendor

Tonylau00

profilemedium
Observed Feb 24, 2026Source linkProvenance
Compatibility (2)

Protocol compatibility

MCP

contracthigh
Observed Feb 24, 2026Source linkProvenance

Auth modes

mcp, api_key

contracthigh
Observed Feb 24, 2026Source linkProvenance
Artifact (1)

Machine-readable schemas

OpenAPI or schema references published

contracthigh
Observed Feb 24, 2026Source linkProvenance
Security (1)

Handshake status

UNKNOWN

trustmedium
Observed unknownSource linkProvenance
Integration (1)

Crawlable docs

6 indexed pages on the official domain

search_documentmedium
Observed Apr 15, 2026Source linkProvenance

Release & Crawl Timeline

Merged public release, docs, artifact, benchmark, pricing, and trust refresh events.

Self-declaredagent-index

Artifacts Archive

Extracted files, examples, snippets, parameters, dependencies, permissions, and artifact metadata.

Self-declaredGITHUB MCP

Extracted files

0

Examples

6

Snippets

0

Languages

typescript

Executable Examples

text

┌─────────────────────────────────────────────────────────┐
│                    mcp-client (SPA)                      │
│                                                         │
│  ┌─────────┐  ┌───────────┐  ┌─────────────────────┐   │
│  │ ChatUI  │  │ ReAct     │  │ LLM Service          │   │
│  │         │──│ Agent     │──│ (7 providers)         │──▶ LLM APIs
│  │         │  │ Loop      │  │ OpenAI/Claude/Gemini/ │   │
│  │         │  │           │  │ DeepSeek/Ollama/...   │   │
│  └────┬────┘  └─────┬─────┘  └─────────────────────┘   │
│       │             │                                    │
│  ┌────▼────┐  ┌─────▼─────┐  ┌─────────────────────┐   │
│  │ Wallet  │  │ MCP SSE   │  │ Graph Viz            │   │
│  │ Connect │  │ Client    │──│ (force-graph-2d)     │   │
│  │ TronLink│  │           │  │ Neo4j Modal          │   │
│  └─────────┘  └─────┬─────┘  └─────────────────────┘   │
│                      │                                   │
└──────────────────────┼───────────────────────────────────┘
                       │ SSE
                       ▼
              tron-mcp-server (:3100)

bash

npm install

bash

cp .env.example .env

dotenv

# MCP Server
VITE_MCP_SERVER_URL=http://localhost:3100

# Default LLM provider
VITE_LLM_PROVIDER=deepseek

# DeepSeek (recommended — cheapest with good tool calling)
VITE_DEEPSEEK_API_KEY=your-key
VITE_DEEPSEEK_BASE_URL=https://api.deepseek.com
VITE_DEEPSEEK_MODEL=deepseek-chat

# OpenAI
VITE_OPENAI_API_KEY=your-key
VITE_OPENAI_MODEL=gpt-4o

# Claude
VITE_CLAUDE_API_KEY=your-key
VITE_CLAUDE_MODEL=claude-sonnet-4-20250514

# Gemini
VITE_GEMINI_API_KEY=your-key
VITE_GEMINI_MODEL=gemini-2.0-flash

# Ollama (local)
VITE_OLLAMA_BASE_URL=http://localhost:11434
VITE_OLLAMA_MODEL=qwen2.5:14b

# OpenRouter
VITE_OPENROUTER_API_KEY=your-key
VITE_OPENROUTER_MODEL=anthropic/claude-sonnet-4

# Custom (OpenAI-compatible)
VITE_CUSTOM_BASE_URL=http://localhost:8000/v1
VITE_CUSTOM_MODEL=default

bash

# Development
npm run dev
# → http://localhost:5173

# Production build
npm run build
# → dist/ (static files, serve with nginx)

bash

npm run build

Docs & README

Full documentation captured from public sources, including the complete README when available.

Self-declaredGITHUB MCP

Docs source

GITHUB MCP

Editorial quality

ready

OpenClaw agent: mcp-client mcp-client A React-based web interface for interacting with the TRON blockchain through a **ReAct (Reasoning + Acting) AI agent**. Connects to an MCP server via SSE, supports **7 LLM providers** with runtime switching, and includes **client-side wallet integration** for signing and broadcasting transactions. Architecture Features AI Agent - **ReAct loop** — multi-step reasoning with tool calling - **7 LLM providers**

Full README

mcp-client

A React-based web interface for interacting with the TRON blockchain through a ReAct (Reasoning + Acting) AI agent. Connects to an MCP server via SSE, supports 7 LLM providers with runtime switching, and includes client-side wallet integration for signing and broadcasting transactions.

Architecture

┌─────────────────────────────────────────────────────────┐
│                    mcp-client (SPA)                      │
│                                                         │
│  ┌─────────┐  ┌───────────┐  ┌─────────────────────┐   │
│  │ ChatUI  │  │ ReAct     │  │ LLM Service          │   │
│  │         │──│ Agent     │──│ (7 providers)         │──▶ LLM APIs
│  │         │  │ Loop      │  │ OpenAI/Claude/Gemini/ │   │
│  │         │  │           │  │ DeepSeek/Ollama/...   │   │
│  └────┬────┘  └─────┬─────┘  └─────────────────────┘   │
│       │             │                                    │
│  ┌────▼────┐  ┌─────▼─────┐  ┌─────────────────────┐   │
│  │ Wallet  │  │ MCP SSE   │  │ Graph Viz            │   │
│  │ Connect │  │ Client    │──│ (force-graph-2d)     │   │
│  │ TronLink│  │           │  │ Neo4j Modal          │   │
│  └─────────┘  └─────┬─────┘  └─────────────────────┘   │
│                      │                                   │
└──────────────────────┼───────────────────────────────────┘
                       │ SSE
                       ▼
              tron-mcp-server (:3100)

Features

AI Agent

  • ReAct loop — multi-step reasoning with tool calling
  • 7 LLM providers — OpenAI, Claude, DeepSeek, Gemini, Ollama (local), OpenRouter, Custom (OpenAI-compatible)
  • Runtime switching — change LLM provider/model without reload
  • Dynamic system prompt — auto-injects wallet address and network context
  • Streaming step display — shows thinking → tool calls → observations → answer in real-time

Blockchain Tools (via MCP)

  • Account balance & resource queries
  • Transaction status & decoded input data
  • Address graph analysis & risk scoring
  • Contract ABI, verification, source code
  • Fund flow analysis
  • Build unsigned TRX/TRC20 transfers (network-aware)

Wallet Integration

  • TronLink browser extension support
  • Private key mode (for testing)
  • Network selector — Mainnet / Nile / Shasta / Custom RPC
  • Client-side signing — transactions are signed locally, never on the server
  • Transaction cards — inline sign & broadcast UI in chat

UI

  • Markdown rendering with code highlighting
  • Neo4j graph modal — interactive force-directed graph visualization
  • Tool explorer side panel — browse all available MCP tools
  • Agent step panel — expandable reasoning trace
  • Dark theme with Tailwind CSS 4

Prerequisites

  • Node.js ≥ 20
  • tron-mcp-server running on port 3100 (SSE mode)
  • At least one LLM API key (DeepSeek, OpenAI, Claude, etc.) or local Ollama

Quick Start

1. Install dependencies

npm install

2. Configure environment

cp .env.example .env

Edit .env:

# MCP Server
VITE_MCP_SERVER_URL=http://localhost:3100

# Default LLM provider
VITE_LLM_PROVIDER=deepseek

# DeepSeek (recommended — cheapest with good tool calling)
VITE_DEEPSEEK_API_KEY=your-key
VITE_DEEPSEEK_BASE_URL=https://api.deepseek.com
VITE_DEEPSEEK_MODEL=deepseek-chat

# OpenAI
VITE_OPENAI_API_KEY=your-key
VITE_OPENAI_MODEL=gpt-4o

# Claude
VITE_CLAUDE_API_KEY=your-key
VITE_CLAUDE_MODEL=claude-sonnet-4-20250514

# Gemini
VITE_GEMINI_API_KEY=your-key
VITE_GEMINI_MODEL=gemini-2.0-flash

# Ollama (local)
VITE_OLLAMA_BASE_URL=http://localhost:11434
VITE_OLLAMA_MODEL=qwen2.5:14b

# OpenRouter
VITE_OPENROUTER_API_KEY=your-key
VITE_OPENROUTER_MODEL=anthropic/claude-sonnet-4

# Custom (OpenAI-compatible)
VITE_CUSTOM_BASE_URL=http://localhost:8000/v1
VITE_CUSTOM_MODEL=default

3. Run

# Development
npm run dev
# → http://localhost:5173

# Production build
npm run build
# → dist/ (static files, serve with nginx)

Production Deployment

Build static files and serve with Nginx:

npm run build

Nginx configuration:

server {
    listen 80;
    server_name your-domain.com;

    root /path/to/mcp-client/dist;
    index index.html;

    # SPA fallback
    location / {
        try_files $uri $uri/ /index.html;
    }

    # Proxy MCP SSE server
    location /mcp/ {
        proxy_pass http://127.0.0.1:3100/;
        proxy_http_version 1.1;
        proxy_set_header Connection '';
        proxy_buffering off;              # Required for SSE
        proxy_cache off;
        proxy_read_timeout 86400s;
    }
}

Project Structure

mcp-client/
├── package.json
├── vite.config.ts
├── tsconfig.json
├── .env.example
├── index.html
└── src/
    ├── main.tsx                    # React entry point
    ├── App.tsx                     # Root component — auto-connects MCP
    ├── config.ts                   # LLM provider configuration (7 providers)
    ├── index.css                   # Tailwind CSS imports
    ├── components/
    │   ├── ChatInterface.tsx       # Main chat UI + agent orchestration
    │   ├── ChatInput.tsx           # Message input with send button
    │   ├── ChatMessage.tsx         # Message bubble with markdown rendering
    │   ├── AgentStepPanel.tsx      # ReAct step trace display
    │   ├── ToolCallPanel.tsx       # Tool invocation details
    │   ├── ToolExplorer.tsx        # Side panel — browse MCP tools
    │   ├── ConnectionSettings.tsx  # MCP server connection config
    │   ├── LlmSettings.tsx         # LLM provider/model selector
    │   ├── WalletConnect.tsx       # Wallet connection + network selector
    │   ├── TransactionCard.tsx     # Inline sign & broadcast card
    │   ├── TransactionConfirmDialog.tsx
    │   ├── TransactionGraph.tsx    # Force-directed graph visualization
    │   ├── Neo4jGraphModal.tsx     # Full-screen graph modal
    │   ├── AddressInfoPanel.tsx    # Address details panel
    │   ├── RiskWarning.tsx         # Risk score warning display
    │   └── ui/                     # Shared UI primitives
    │       ├── Badge.tsx
    │       ├── Button.tsx
    │       ├── Card.tsx
    │       ├── Dialog.tsx
    │       └── Input.tsx
    ├── lib/
    │   ├── agent.ts               # ReAct agent loop
    │   ├── llm-service.ts         # Multi-provider LLM service
    │   ├── mcp-client.ts          # MCP SSE client wrapper
    │   ├── tron-wallet.ts         # TronLink / private key wallet
    │   └── utils.ts               # Helpers (truncateAddress, cn, etc.)
    └── store/
        └── index.ts               # Zustand stores (MCP, Chat, Agent, LLM, Wallet, UI)

State Management

Six Zustand stores:

| Store | Purpose | |-------|---------| | useMcpStore | MCP connection state, available tools | | useChatStore | Chat messages, pending tool calls | | useAgentStore | Agent steps, running state | | useLlmStore | Active provider, model, all provider configs | | useWalletStore | Wallet mode, address, network, pending transactions | | useUiStore | Theme, panel visibility |

Usage Examples

  1. Check address balance:

    "What's the balance of TR7NHqjeKQxGTCi8q8ZY4pL8otSzgjLj6t?"

  2. Analyze address risk:

    "Is address TDqSquXBgUCLYvYC4XZgrprLK589dkhSCf safe to interact with?"

  3. Build a transfer:

    "Send 100 TRX to TAddr..." (auto-uses connected wallet as sender)

  4. Explore transaction graph:

    "Show me the transaction network around address TXyz... with 2 hops"

  5. Inspect a contract:

    "What does the contract TXYZopYRdj2D9XRtbG411XZZ3kM5VkAeBf do?"

Tech Stack

| Component | Technology | |-----------|-----------| | Framework | React 19 | | Build Tool | Vite 7 | | Language | TypeScript ~5.9 | | Styling | Tailwind CSS 4 | | State | Zustand 5 | | Graphs | react-force-graph-2d | | Markdown | react-markdown + remark-gfm | | Icons | Lucide React | | Blockchain | TronWeb ^6.2.0 | | MCP | @modelcontextprotocol/sdk ^1.26.0 | | Data Fetching | @tanstack/react-query 5 |

License

MIT

Contract & API

Machine endpoints, protocol fit, contract coverage, invocation examples, and guardrails for agent-to-agent use.

Verifiedcapability-contract

Contract coverage

Status

ready

Auth

mcp, api_key

Streaming

Yes

Data region

global

Protocol support

MCP: verified

Requires: mcp, lang:typescript, streaming

Forbidden: none

Guardrails

Operational confidence: medium

Contract is available with explicit auth and schema references.
Trust confidence is not low and verification freshness is acceptable.
Protocol support is explicitly confirmed in contract metadata.
Invocation examples
curl -s "https://xpersona.co/api/v1/agents/mcp-tonylau00-mcp-client/snapshot"
curl -s "https://xpersona.co/api/v1/agents/mcp-tonylau00-mcp-client/contract"
curl -s "https://xpersona.co/api/v1/agents/mcp-tonylau00-mcp-client/trust"

Reliability & Benchmarks

Trust and runtime signals, benchmark suites, failure patterns, and practical risk constraints.

Missingruntime-metrics

Trust signals

Handshake

UNKNOWN

Confidence

unknown

Attempts 30d

unknown

Fallback rate

unknown

Runtime metrics

Observed P50

unknown

Observed P95

unknown

Rate limit

unknown

Estimated cost

unknown

No benchmark suites or observed failure patterns are available.

Media & Demo

Every public screenshot, visual asset, demo link, and owner-provided destination tied to this agent.

Missingno-media
No screenshots, media assets, or demo links are available.

Related Agents

Neighboring agents from the same protocol and source ecosystem for comparison and shortlist building.

Self-declaredprotocol-neighbors
GITLAB_AI_CATALOGgitlab-mcp

Rank

83

A Model Context Protocol (MCP) server for GitLab

Traction

No public download signal

Freshness

Updated 2d ago

MCP
GITLAB_PUBLIC_PROJECTSgitlab-mcp

Rank

80

A Model Context Protocol (MCP) server for GitLab

Traction

No public download signal

Freshness

Updated 2d ago

MCP
GITLAB_AI_CATALOGrmcp-openapi

Rank

74

Expose OpenAPI definition endpoints as MCP tools using the official Rust SDK for the Model Context Protocol (https://github.com/modelcontextprotocol/rust-sdk)

Traction

No public download signal

Freshness

Updated 2d ago

MCP
GITLAB_AI_CATALOGrmcp-actix-web

Rank

72

An actix_web backend for the official Rust SDK for the Model Context Protocol (https://github.com/modelcontextprotocol/rust-sdk)

Traction

No public download signal

Freshness

Updated 2d ago

MCP
Machine Appendix

Contract JSON

{
  "contractStatus": "ready",
  "authModes": [
    "mcp",
    "api_key"
  ],
  "requires": [
    "mcp",
    "lang:typescript",
    "streaming"
  ],
  "forbidden": [],
  "supportsMcp": true,
  "supportsA2a": false,
  "supportsStreaming": true,
  "inputSchemaRef": "https://github.com/TonyLau00/mcp-client#input",
  "outputSchemaRef": "https://github.com/TonyLau00/mcp-client#output",
  "dataRegion": "global",
  "contractUpdatedAt": "2026-02-24T19:46:45.542Z",
  "sourceUpdatedAt": "2026-02-24T19:46:45.542Z",
  "freshnessSeconds": 4440593
}

Invocation Guide

{
  "preferredApi": {
    "snapshotUrl": "https://xpersona.co/api/v1/agents/mcp-tonylau00-mcp-client/snapshot",
    "contractUrl": "https://xpersona.co/api/v1/agents/mcp-tonylau00-mcp-client/contract",
    "trustUrl": "https://xpersona.co/api/v1/agents/mcp-tonylau00-mcp-client/trust"
  },
  "curlExamples": [
    "curl -s \"https://xpersona.co/api/v1/agents/mcp-tonylau00-mcp-client/snapshot\"",
    "curl -s \"https://xpersona.co/api/v1/agents/mcp-tonylau00-mcp-client/contract\"",
    "curl -s \"https://xpersona.co/api/v1/agents/mcp-tonylau00-mcp-client/trust\""
  ],
  "jsonRequestTemplate": {
    "query": "summarize this repo",
    "constraints": {
      "maxLatencyMs": 2000,
      "protocolPreference": [
        "MCP"
      ]
    }
  },
  "jsonResponseTemplate": {
    "ok": true,
    "result": {
      "summary": "...",
      "confidence": 0.9
    },
    "meta": {
      "source": "GITHUB_MCP",
      "generatedAt": "2026-04-17T05:16:38.757Z"
    }
  },
  "retryPolicy": {
    "maxAttempts": 3,
    "backoffMs": [
      500,
      1500,
      3500
    ],
    "retryableConditions": [
      "HTTP_429",
      "HTTP_503",
      "NETWORK_TIMEOUT"
    ]
  }
}

Trust JSON

{
  "status": "unavailable",
  "handshakeStatus": "UNKNOWN",
  "verificationFreshnessHours": null,
  "reputationScore": null,
  "p95LatencyMs": null,
  "successRate30d": null,
  "fallbackRate": null,
  "attempts30d": null,
  "trustUpdatedAt": null,
  "trustConfidence": "unknown",
  "sourceUpdatedAt": null,
  "freshnessSeconds": null
}

Capability Matrix

{
  "rows": [
    {
      "key": "MCP",
      "type": "protocol",
      "support": "supported",
      "confidenceSource": "contract",
      "notes": "Confirmed by capability contract"
    }
  ],
  "flattenedTokens": "protocol:MCP|supported|contract"
}

Facts JSON

[
  {
    "factKey": "docs_crawl",
    "category": "integration",
    "label": "Crawlable docs",
    "value": "6 indexed pages on the official domain",
    "href": "https://github.com/login?return_to=https%3A%2F%2Fgithub.com%2Fopenclaw%2Fskills%2Ftree%2Fmain%2Fskills%2Fasleep123%2Fcaldav-calendar",
    "sourceUrl": "https://github.com/login?return_to=https%3A%2F%2Fgithub.com%2Fopenclaw%2Fskills%2Ftree%2Fmain%2Fskills%2Fasleep123%2Fcaldav-calendar",
    "sourceType": "search_document",
    "confidence": "medium",
    "observedAt": "2026-04-15T05:03:46.393Z",
    "isPublic": true
  },
  {
    "factKey": "protocols",
    "category": "compatibility",
    "label": "Protocol compatibility",
    "value": "MCP",
    "href": "https://xpersona.co/api/v1/agents/mcp-tonylau00-mcp-client/contract",
    "sourceUrl": "https://xpersona.co/api/v1/agents/mcp-tonylau00-mcp-client/contract",
    "sourceType": "contract",
    "confidence": "high",
    "observedAt": "2026-02-24T19:46:45.542Z",
    "isPublic": true
  },
  {
    "factKey": "auth_modes",
    "category": "compatibility",
    "label": "Auth modes",
    "value": "mcp, api_key",
    "href": "https://xpersona.co/api/v1/agents/mcp-tonylau00-mcp-client/contract",
    "sourceUrl": "https://xpersona.co/api/v1/agents/mcp-tonylau00-mcp-client/contract",
    "sourceType": "contract",
    "confidence": "high",
    "observedAt": "2026-02-24T19:46:45.542Z",
    "isPublic": true
  },
  {
    "factKey": "schema_refs",
    "category": "artifact",
    "label": "Machine-readable schemas",
    "value": "OpenAPI or schema references published",
    "href": "https://github.com/TonyLau00/mcp-client#input",
    "sourceUrl": "https://xpersona.co/api/v1/agents/mcp-tonylau00-mcp-client/contract",
    "sourceType": "contract",
    "confidence": "high",
    "observedAt": "2026-02-24T19:46:45.542Z",
    "isPublic": true
  },
  {
    "factKey": "vendor",
    "category": "vendor",
    "label": "Vendor",
    "value": "Tonylau00",
    "href": "https://github.com/TonyLau00/mcp-client",
    "sourceUrl": "https://github.com/TonyLau00/mcp-client",
    "sourceType": "profile",
    "confidence": "medium",
    "observedAt": "2026-02-24T19:43:14.176Z",
    "isPublic": true
  },
  {
    "factKey": "handshake_status",
    "category": "security",
    "label": "Handshake status",
    "value": "UNKNOWN",
    "href": "https://xpersona.co/api/v1/agents/mcp-tonylau00-mcp-client/trust",
    "sourceUrl": "https://xpersona.co/api/v1/agents/mcp-tonylau00-mcp-client/trust",
    "sourceType": "trust",
    "confidence": "medium",
    "observedAt": null,
    "isPublic": true
  }
]

Change Events JSON

[
  {
    "eventType": "docs_update",
    "title": "Docs refreshed: Sign in to GitHub · GitHub",
    "description": "Fresh crawlable documentation was indexed for the official domain.",
    "href": "https://github.com/login?return_to=https%3A%2F%2Fgithub.com%2Fopenclaw%2Fskills%2Ftree%2Fmain%2Fskills%2Fasleep123%2Fcaldav-calendar",
    "sourceUrl": "https://github.com/login?return_to=https%3A%2F%2Fgithub.com%2Fopenclaw%2Fskills%2Ftree%2Fmain%2Fskills%2Fasleep123%2Fcaldav-calendar",
    "sourceType": "search_document",
    "confidence": "medium",
    "observedAt": "2026-04-15T05:03:46.393Z",
    "isPublic": true
  }
]

Sponsored

Ads related to mcp-client and adjacent AI workflows.