Native MCP

Native MCP Client

Hermes Agent has a built-in MCP client that connects to MCP servers at startup, discovers their tools, and makes them available as first-class tools the agent can call directly. No bridge CLI needed -- tools from MCP servers appear alongside built-in tools like terminal, read_file, etc.

When to Use

Use this whenever you want to:

• Connect to MCP servers and use their tools from within Hermes Agent
• Add external capabilities (filesystem access, GitHub, databases, APIs) via MCP
• Run local stdio-based MCP servers (npx, uvx, or any command)
• Connect to remote HTTP/StreamableHTTP MCP servers
• Have MCP tools auto-discovered and available in every conversation

For ad-hoc, one-off MCP tool calls from the terminal without configuring anything, see the mcporter skill instead.

Prerequisites

• mcp Python package -- optional dependency; install with pip install mcp. If not installed, MCP support is silently disabled.
• Node.js -- required for npx-based MCP servers (most community servers)
• uv -- required for uvx-based MCP servers (Python-based servers)

Install the MCP SDK:

pip install mcp
# or, if using uv:
uv pip install mcp

Quick Start

Add MCP servers to ~/.hermes/config.yaml under the mcp_servers key:

mcp_servers:
  time:
    command: "uvx"
    args: ["mcp-server-time"]

Restart Hermes Agent. On startup it will:

1. Connect to the server
2. Discover available tools
3. Register them with the prefix mcp_time_*
4. Inject them into all platform toolsets

You can then use the tools naturally -- just ask the agent to get the current time.

Configuration Reference

Each entry under mcp_servers is a server name mapped to its config. There are two transport types: stdio (command-based) and HTTP (url-based).

Stdio Transport (command + args)

mcp_servers:
  server_name:
    command: "npx"             # (required) executable to run
    args: ["-y", "pkg-name"]   # (optional) command arguments, default: []
    env:                       # (optional) environment variables for the subprocess
      SOME_API_KEY: "value"
    timeout: 120               # (optional) per-tool-call timeout in seconds, default: 120
    connect_timeout: 60        # (optional) initial connection timeout in seconds, default: 60

HTTP Transport (url)

mcp_servers:
  server_name:
    url: "https://my-server.example.com/mcp"   # (required) server URL
    headers:                                     # (optional) HTTP headers
      Authorization: "Bearer sk-..."
    timeout: 180               # (optional) per-tool-call timeout in seconds, default: 120
    connect_timeout: 60        # (optional) initial connection timeout in seconds, default: 60

All Config Options

Note: A server config must have either command (stdio) or url (HTTP), not both.

How It Works

Startup Discovery

When Hermes Agent starts, discover_mcp_tools() is called during tool initialization:

1. Reads mcp_servers from ~/.hermes/config.yaml
2. For each server, spawns a connection in a dedicated background event loop
3. Initializes the MCP session and calls list_tools() to discover available tools
4. Registers each tool in the Hermes tool registry

Tool Naming Convention

MCP tools are registered with the naming pattern:

mcp_{server_name}_{tool_name}

Hyphens and dots in names are replaced with underscores for LLM API compatibility.

Examples:

• Server filesystem, tool read_file → mcp_filesystem_read_file
• Server github, tool list-issues → mcp_github_list_issues
• Server my-api, tool fetch.data → mcp_my_api_fetch_data

Auto-Injection

After discovery, MCP tools are automatically injected into all hermes-* platform toolsets (CLI, Discord, Telegram, etc.). This means MCP tools are available in every conversation without any additional configuration.

Connection Lifecycle

• Each server runs as a long-lived asyncio Task in a background daemon thread
• Connections persist for the lifetime of the agent process
• If a connection drops, automatic reconnection with exponential backoff kicks in (up to 5 retries, max 60s backoff)
• On agent shutdown, all connections are gracefully closed

Idempotency

discover_mcp_tools() is idempotent -- calling it multiple times only connects to servers that aren't already connected. Failed servers are retried on subsequent calls.

Transport Types

Stdio Transport

The most common transport. Hermes launches the MCP server as a subprocess and communicates over stdin/stdout.

mcp_servers:
  filesystem:
    command: "npx"
    args: ["-y", "@modelcontextprotocol/server-filesystem", "/home/user/projects"]

The subprocess inherits a filtered environment (see Security section below) plus any variables you specify in env.

HTTP / StreamableHTTP Transport

For remote or shared MCP servers. Requires the mcp package to include HTTP client support (mcp.client.streamable_http).

mcp_servers:
  remote_api:
    url: "https://mcp.example.com/mcp"
    headers:
      Authorization: "Bearer sk-..."

If HTTP support is not available in your installed mcp version, the server will fail with an ImportError and other servers will continue normally.

Security

Environment Variable Filtering

For stdio servers, Hermes does NOT pass your full shell environment to MCP subprocesses. Only safe baseline variables are inherited:

• PATH, HOME, USER, LANG, LC_ALL, TERM, SHELL, TMPDIR
• Any XDG_* variables

All other environment variables (API keys, tokens, secrets) are excluded unless you explicitly add them via the env config key. This prevents accidental credential leakage to untrusted MCP servers.

mcp_servers:
  github:
    command: "npx"
    args: ["-y", "@modelcontextprotocol/server-github"]
    env:
      # Only this token is passed to the subprocess
      GITHUB_PERSONAL_ACCESS_TOKEN: "ghp_..."

Credential Stripping in Error Messages

If an MCP tool call fails, any credential-like patterns in the error message are automatically redacted before being shown to the LLM. This covers:

• GitHub PATs (ghp_...)
• OpenAI-style keys (sk-...)
• Bearer tokens
• Generic token=, key=, API_KEY=, password=, secret= patterns

Troubleshooting

"MCP SDK not available -- skipping MCP tool discovery"

The mcp Python package is not installed. Install it:

pip install mcp

"No MCP servers configured"

No mcp_servers key in ~/.hermes/config.yaml, or it's empty. Add at least one server.

"Failed to connect to MCP server 'X'"

Common causes:

• Command not found: The command binary isn't on PATH. Ensure npx, uvx, or the relevant command is installed.
• Package not found: For npx servers, the npm package may not exist or may need -y in args to auto-install.
• Timeout: The server took too long to start. Increase connect_timeout.
• Port conflict: For HTTP servers, the URL may be unreachable.

"MCP server 'X' requires HTTP transport but mcp.client.streamable_http is not available"

Your mcp package version doesn't include HTTP client support. Upgrade:

pip install --upgrade mcp

Tools not appearing

• Check that the server is listed under mcp_servers (not mcp or servers)
• Ensure the YAML indentation is correct
• Look at Hermes Agent startup logs for connection messages
• Tool names are prefixed with mcp_{server}_{tool} -- look for that pattern

"MCP server 'X' is unreachable after N consecutive failures"

Symptoms: ps aux shows the server process running, but hermes-agent tool calls fail with TimeoutError. Direct curl to the server's HTTP endpoint returns Not Found or other unexpected responses.

Root cause patterns:

1. Server running but not responding to MCP protocol — curl http://localhost:3333/ returns something like "Not Found" even though the process is alive. This means the server is running but the endpoint path or headers are wrong.

2. Missing HTTP protocol headers — MCP HTTP servers (especially StreamableHTTP transport) require specific headers on every request:

   • Accept: application/json, text/event-stream — server rejects requests without this
   • Content-Type: application/json

   Without these, the server returns 406 or other errors.

3. Missing session ID — StreamableHTTP MCP servers require an MCP-Session-ID header, obtained from the initialize response's mcp-session-id header. Without it, subsequent calls fail with Invalid request parameters.

Diagnosis with curl (HTTP servers):

# Test if server is alive at all
curl -s --max-time 5 http://localhost:3333/ && echo "Server alive"

# Test MCP initialize (check response headers for mcp-session-id)
curl -s --max-time 10 -i -X POST http://localhost:3333/mcp \
  -H "Content-Type: application/json" \
  -H "Accept: application/json, text/event-stream" \
  -d '{"jsonrpc":"2.0","method":"initialize","params":{"protocolVersion":"2024-11-05","capabilities":{},"clientInfo":{"name":"test","version":"1.0"}},"id":1}' 2>&1

# If you see "Not Acceptable" → missing Accept header
# If you see "Missing session ID" → server requires MCP-Session-ID header
# If you see a valid JSON response with serverInfo → server is healthy

Fix approaches (in order of preference):

1. Restart the MCP server process — often resolves transient state issues:

   pkill -f "mcp_server.server --transport=http --port=3333"
   sleep 2
   # Restart with same command from original launch
   

2. Check server logs — look for startup errors, port conflicts, import failures:

   cat /tmp/trendradar_mcp.log 2>/dev/null || journalctl | grep mcp
   

3. Verify config.yaml — some MCP servers require a config file:

   cd /path/to/mcp/server && ls -la config.yaml 2>/dev/null
   

Important: If ps aux shows the server running but hermes-agent still fails, the server process may be in a broken state (e.g., an import error at startup that caused it to crash after backgrounding). Restarting the process often fixes it. Do NOT assume "process running = working."

Connection keeps dropping

The client retries up to 5 times with exponential backoff (1s, 2s, 4s, 8s, 16s, capped at 60s). If the server is fundamentally unreachable, it gives up after 5 attempts. Check the server process and network connectivity.

Examples

Time Server (uvx)

mcp_servers:
  time:
    command: "uvx"
    args: ["mcp-server-time"]

Registers tools like mcp_time_get_current_time.

Filesystem Server (npx)

mcp_servers:
  filesystem:
    command: "npx"
    args: ["-y", "@modelcontextprotocol/server-filesystem", "/home/user/documents"]
    timeout: 30

Registers tools like mcp_filesystem_read_file, mcp_filesystem_write_file, mcp_filesystem_list_directory.

GitHub Server with Authentication

mcp_servers:
  github:
    command: "npx"
    args: ["-y", "@modelcontextprotocol/server-github"]
    env:
      GITHUB_PERSONAL_ACCESS_TOKEN: "[REDACTED]"
    timeout: 60

Registers tools like mcp_github_list_issues, mcp_github_create_pull_request, etc.

Remote HTTP Server

mcp_servers:
  company_api:
    url: "https://mcp.mycompany.com/v1/mcp"
    headers:
      Authorization: "Bearer sk-xxxxxxxxxxxxxxxxxxxx"
      X-Team-Id: "engineering"
    timeout: 180
    connect_timeout: 30

Multiple Servers

mcp_servers:
  time:
    command: "uvx"
    args: ["mcp-server-time"]

  filesystem:
    command: "npx"
    args: ["-y", "@modelcontextprotocol/server-filesystem", "/tmp"]

  github:
    command: "npx"
    args: ["-y", "@modelcontextprotocol/server-github"]
    env:
      GITHUB_PERSONAL_ACCESS_TOKEN: "[REDACTED]"

  company_api:
    url: "https://mcp.internal.company.com/mcp"
    headers:
      Authorization: "Bearer sk-xxxxxxxxxxxxxxxxxxxx"
    timeout: 300

All tools from all servers are registered and available simultaneously. Each server's tools are prefixed with its name to avoid collisions.

Sampling (Server-Initiated LLM Requests)

Hermes supports MCP's sampling/createMessage capability — MCP servers can request LLM completions through the agent during tool execution. This enables agent-in-the-loop workflows (data analysis, content generation, decision-making).

Sampling is enabled by default. Configure per server:

mcp_servers:
  my_server:
    command: "npx"
    args: ["-y", "my-mcp-server"]
    sampling:
      enabled: true           # default: true
      model: "gemini-3-flash" # model override (optional)
      max_tokens_cap: 4096    # max tokens per request
      timeout: 30             # LLM call timeout (seconds)
      max_rpm: 10             # max requests per minute
      allowed_models: []      # model whitelist (empty = all)
      max_tool_rounds: 5      # tool loop limit (0 = disable)
      log_level: "info"       # audit verbosity

Servers can also include tools in sampling requests for multi-turn tool-augmented workflows. The max_tool_rounds config prevents infinite tool loops. Per-server audit metrics (requests, errors, tokens, tool use count) are tracked via get_mcp_status().

Disable sampling for untrusted servers with sampling: { enabled: false }.

Notes

• MCP tools are called synchronously from the agent's perspective but run asynchronously on a dedicated background event loop
• Tool results are returned as JSON with either {"result": "..."} or {"error": "..."}
• The native MCP client is independent of mcporter -- you can use both simultaneously
• Server connections are persistent and shared across all conversations in the same agent process
• Adding or removing servers requires restarting the agent (no hot-reload currently)