# AgentExec WebMCP & Base L2 Gateway (remote · api.agentexec.dev)

Monetization and execution gateway for autonomous AI agents on Base Mainnet

- Trust score: 65/100 (medium)
- Change this week: +6
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-09-20

> **Recent critical change**: Authorization (2026-09-14). See the changelog below before you install this server.

## Components

- remote · `api.agentexec.dev`: 65/100 (this document), [markdown](https://verifymcp.io/servers/har50-gateway/api.md), [page](https://verifymcp.io/servers/har50-gateway/api)

## Channel facts

- Endpoint: `https://api.agentexec.dev/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `1.0.2`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-09-20.

- **Endpoint Security**: 57/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation check failed: no authorisation is required to call this server, and it exposes a tool marked destructive (execute_onchain_intent).
  - HTTPS is enforced; there's no plaintext access path.
  - HSTS check failed: the Strict-Transport-Security header is absent.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 67/100
  - AI-judged instruction clarity (good).
  - Tool/resource definitions use about 449 tokens (~112/item across 4 items; 4 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 23/100
  - Stability observed for 7 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 81/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 44% of tool parameters carry a description.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - All 1 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation.
  - An AI judge read all 5 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### How do I install the AgentExec WebMCP & Base L2 Gateway MCP server?

AgentExec WebMCP & Base L2 Gateway is a hosted endpoint at https://api.agentexec.dev/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add --transport http har50-gateway 'https://api.agentexec.dev/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "har50-gateway": {
      "url": "https://api.agentexec.dev/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "har50-gateway": {
      "type": "http",
      "url": "https://api.agentexec.dev/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.har50-gateway]
url = "https://api.agentexec.dev/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "har50-gateway": {
      "type": "remote",
      "url": "https://api.agentexec.dev/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add har50-gateway --url 'https://api.agentexec.dev/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  har50-gateway:
    url: "https://api.agentexec.dev/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "har50-gateway": {
      "Transport": "http",
      "Url": "https://api.agentexec.dev/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add har50-gateway -t streamable-http -u 'https://api.agentexec.dev/mcp'
```

### Other

```json
{
  "mcpServers": {
    "har50-gateway": {
      "type": "http",
      "url": "https://api.agentexec.dev/mcp"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-09-20 (score 65, +1)

No change was recorded against any check on this day. Stability & Change Management went from 20 to 23. That category is still filling its 30-day observation window: 6 days of observed history at the previous scan, 7 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-18 (score 64, +1)

No change was recorded against any check on this day. Stability & Change Management went from 13 to 17. That category is still filling its 30-day observation window: 4 days of observed history at the previous scan, 5 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-16 (score 63, +1)

No change was recorded against any check on this day. Stability & Change Management went from 7 to 10. That category is still filling its 30-day observation window: 2 days of observed history at the previous scan, 3 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-14 (score 62, +3)

- [critical regression] Authorization: unverified → fail
- [security] The server rewrote its instructions, which are the text every model session reads
- [security] Tool “dry_run_simulation” rewrote its description, which is the text the model reads
- [security] Tool “execute_onchain_intent” rewrote its description, which is the text the model reads
- [security] Tool “get_smart_account_info” rewrote its description, which is the text the model reads
- [security] Tool “issue_session_key” rewrote its description, which is the text the model reads
- [security] Tool “execute_onchain_intent” is now declared destructive
- [functional regression] Schema quality: 90 → 112
- [functional improvement] Stability: unverified → 0.03
- [functional] Destructive annotations: All 1 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation.

### 2026-09-13 (score 59, +36)

- [security improvement] Injection markers: unverified → pass
- [security improvement] Transport: fail → pass
- [security] First check of Judged manipulation: pass
- [security] Authorization: Authorisation not fully verified: no authorisation is required to call this server, and 4 tool(s) never declared a destructiveHint. The MCP spec treats an absent hint as destructive by default, so we cannot call this surface safe.
- [functional improvement] Tool coverage: unverified → 100
- [functional improvement] MCP protocol: unverified → pass
- [functional] First check of Schema quality: fail
- [functional] First check of Destructive annotations: 0
- [functional] First check of Schema quality: pass
- [functional] First check of Schema quality: good
- [functional] First check of Tool coverage: 44

### 2026-09-05 (score 23)

First indexed and scored.

## MCP tools (4)

### `execute_onchain_intent` (~170 tokens)

Simulates and executes a gasless, sponsored Web3 transaction on Base L2 (e.g. token swaps, transfers). Runs Tenderly dry-run safety checks automatically before broadcasting. Requires an API key.

Input parameters:

- `agentId` (string): Agent identifier for session scoping.
- `calldata` (string, required): Hex-encoded transaction calldata.
- `fromAddress` (string, required): The Safe Smart Account address performing the action.
- `maxAllowedDrainUSD` (number): Maximum allowable wallet drain in USD during simulation guardrail check.
- `sessionKeyId` (string): Optional ERC-7579 session key id to enforce spend/target caps.
- `targetAddress` (string, required): Target contract or token recipient address.
- `valueWei` (string): Native token value in Wei (defaults to '0').

### `get_smart_account_info` (~35 tokens)

Retrieves the Agent Owner EOA address and counterfactual Safe Smart Wallet address on Base. Works without an API key.

### `dry_run_simulation` (~87 tokens)

Simulates a transaction on Tenderly without broadcasting. Returns predicted gas and balance changes. Works without an API key (rate-limited per client) unless the operator disables public simulation.

Input parameters:

- `calldata` (string, required)
- `fromAddress` (string, required)
- `maxAllowedDrainUSD` (number)
- `targetAddress` (string, required)
- `valueWei` (string)

### `issue_session_key` (~71 tokens)

Issue an ERC-7579 / ZeroDev-scoped session key (time limit, USDC spend cap, target whitelist). Requires an API key.

Input parameters:

- `agentId` (string, required)
- `maxUsdc` (number)
- `target` (string)
- `ttlHours` (number)

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/har50-gateway/api#diagnostics

## Score history

- 2026-09-20: 65
- 2026-09-19: 64
- 2026-09-18: 64
- 2026-09-17: 63
- 2026-09-16: 63
- 2026-09-15: 62
- 2026-09-14: 62
- 2026-09-13: 59
- 2026-09-12: 23
- 2026-09-11: 23
- 2026-09-10: 23
- 2026-09-09: 23
- 2026-09-08: 23
- 2026-09-07: 23
- 2026-09-06: 23
- 2026-09-05: 23

## Common questions

### What is the AgentExec WebMCP & Base L2 Gateway MCP server?

AgentExec WebMCP & Base L2 Gateway is an MCP server listed in the public MCP registry as io.github.Har50/gateway. Monetization and execution gateway for autonomous AI agents on Base Mainnet. This page covers its hosted endpoint (https://api.agentexec.dev/mcp).

### Is the AgentExec WebMCP & Base L2 Gateway MCP server safe to use?

AgentExec WebMCP & Base L2 Gateway scores 65 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the AgentExec WebMCP & Base L2 Gateway MCP server expose?

AgentExec WebMCP & Base L2 Gateway exposes 4 tools: execute_onchain_intent, get_smart_account_info, dry_run_simulation, issue_session_key. Their descriptions and schemas cost roughly 363 tokens of context every time the server is loaded.

### Does the AgentExec WebMCP & Base L2 Gateway MCP server require authentication?

No. We connected to AgentExec WebMCP & Base L2 Gateway without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

### Is the AgentExec WebMCP & Base L2 Gateway MCP server still maintained?

AgentExec WebMCP & Base L2 Gateway is still listed as active in the MCP registry. We last reached this channel on 20 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

## Links

- Remote endpoint: https://api.agentexec.dev/mcp
- Repository: https://github.com/Har50/agent1
- Website: https://agentexec.dev/
- Changelog RSS feed: https://verifymcp.io/servers/har50-gateway/api.xml
- Changelog JSON feed: https://verifymcp.io/servers/har50-gateway/api.json
- HTML version of this page: https://verifymcp.io/servers/har50-gateway/api