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.

Installing a Python-based MCP Server (End-to-End)

Many PyPI-published MCP servers need permanent installation rather than ephemeral uvx/npx. This workflow covers the full cycle: install, test, configure.

Step 1 — Create a venv

On Debian/Ubuntu (PEP 668), system pip is blocked. Use an isolated venv:

python3 -m venv ~/.hermes/venvs/<server-name>
~/.hermes/venvs/<server-name>/bin/pip install <package-name>

Step 2 — Verify the binary

Confirm the server executable starts cleanly:

~/.hermes/venvs/<server-name>/bin/<binary-name> --help

Step 3 — Test via the MCP SDK

Before wiring into Hermes, validate the server speaks correct MCP protocol. This catches protocol issues, missing dependencies, and auth failures before they surface as opaque “Failed to connect” errors:

import asyncio
from mcp import ClientSession, StdioServerParameters
from mcp.client.stdio import stdio_client

async def test():
    params = StdioServerParameters(command='/path/to/venv/bin/binary')
    async with stdio_client(params) as (read, write):
        async with ClientSession(read, write) as session:
            await session.initialize()
            tools = await session.list_tools()
            for t in tools.tools:
                print(f'  {t.name}: {t.description}')
            # Optional: call a tool
            # result = await session.call_tool('tool_name', {'arg': 'value'})

asyncio.run(test())

Step 4 — Configure in Hermes

Point to the venv binary directly:

mcp_servers:
  my-server:
    command: "/home/user/.hermes/venvs/<server-name>/bin/<binary-name>"

Or via the CLI (no YAML editing):

hermes config set mcp_servers.<server-name>.command /path/to/venv/bin/binary

Step 5 — (Optional) Integrate with Claude Code CLI

If Claude Code CLI is also used, register the same server there:

claude mcp add <server-name> -- /path/to/venv/bin/binary

Verify with:

claude mcp list | grep <server-name>

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

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.

How to verify a server before wiring it into Hermes

Use the Python MCP SDK to test the server directly (see Step 3 in the Installation section above for a complete test script). This confirms the server starts, initializes correctly, and exposes the expected tools. Run this test before editing config.yaml — it isolates protocol issues from Hermes configuration issues.

Common pitfalls with venv-based servers

• PATH mismatch: The command in mcp_servers must be the full absolute path to the venv binary, not just the binary name. Hermes filters environment variables and may not have the venv’s bin/ on PATH.
• PEP 668 blockers: On Debian 12+/Ubuntu 24.04+, pip install fails on system Python. Always use a venv.
• Missing mcp package: The server binary is a thin wrapper; it depends on mcp (transitively installed via the server package). If the server package has a broken dependency, install mcp explicitly in the venv.

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: "ghp_xxxxxxxxxxxxxxxxxxxx"
    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: "ghp_xxxxxxxxxxxxxxxxxxxx"

  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)

Absorbed: MCP Manager

references/mcp-manager.md — Operational MCP server management in config.yaml: list active servers, disable heavy ones, wrap as JIT skills, Coolify integration. Previously a standalone skill (mcp-manager).

Absorbed: Token Audit

references/token-audit.md — MCP token cost analysis: inventory active MCPs, estimate per-component token costs, produce timestamped .md report. Previously a standalone skill (token-audit). Use for cost optimization and MCP footprint analysis.