Files
hermes-agent/website/docs/reference/mcp-config-reference.md
Teknium 7e0c2c3ce3 docs: comprehensive documentation audit — fix 9 HIGH, 20+ MEDIUM gaps (#4087)
Reference docs fixes:
- cli-commands.md: remove non-existent --provider alibaba, add hermes
  profile/completion/plugins/mcp to top-level table, add --profile/-p
  global flag, add --source chat option
- slash-commands.md: add /yolo and /commands, fix /q alias conflict
  (resolves to /queue not /quit), add missing aliases (/bg, /set-home,
  /reload_mcp, /gateway)
- toolsets-reference.md: fix hermes-api-server (not same as hermes-cli,
  omits clarify/send_message/text_to_speech)
- profile-commands.md: fix show name required not optional, --clone-from
  not --from, add --remove/--name to alias, fix alias path, fix export/
  import arg types, remove non-existent fish completion
- tools-reference.md: add EXA_API_KEY to web tools requires_env
- mcp-config-reference.md: add auth key for OAuth, tool name sanitization
- environment-variables.md: add EXA_API_KEY, update provider values
- plugins.md: remove non-existent ctx.register_command(), add
  ctx.inject_message()

Feature docs additions:
- security.md: add /yolo mode, approval modes (manual/smart/off),
  configurable timeout, expanded dangerous patterns table
- cron.md: add wrap_response config, [SILENT] suppression
- mcp.md: add dynamic tool discovery, MCP sampling support
- cli.md: add Ctrl+Z suspend, busy_input_mode, tool_preview_length
- docker.md: add skills/credential file mounting

Messaging platform docs:
- telegram.md: add webhook mode, DoH fallback IPs
- slack.md: add multi-workspace OAuth support
- discord.md: add DISCORD_IGNORE_NO_MENTION
- matrix.md: add MSC3245 native voice messages
- feishu.md: expand from 129 to 365 lines (encrypt key, verification
  token, group policy, card actions, media, rate limiting, markdown,
  troubleshooting)
- wecom.md: expand from 86 to 264 lines (per-group allowlists, media,
  AES decryption, stream replies, reconnection, troubleshooting)

Configuration docs:
- quickstart.md: add DeepSeek, Copilot, Copilot ACP providers
- configuration.md: add DeepSeek provider, Exa web backend, terminal
  env_passthrough/images, browser.command_timeout, compression params,
  discord config, security/tirith config, timezone, auxiliary models

21 files changed, ~1000 lines added
2026-03-30 17:15:21 -07:00

5.7 KiB

sidebar_position, title, description
sidebar_position title description
8 MCP Config Reference Reference for Hermes Agent MCP configuration keys, filtering semantics, and utility-tool policy

MCP Config Reference

This page is the compact reference companion to the main MCP docs.

For conceptual guidance, see:

Root config shape

mcp_servers:
  <server_name>:
    command: "..."      # stdio servers
    args: []
    env: {}

    # OR
    url: "..."          # HTTP servers
    headers: {}

    enabled: true
    timeout: 120
    connect_timeout: 60
    tools:
      include: []
      exclude: []
      resources: true
      prompts: true

Server keys

Key Type Applies to Meaning
command string stdio Executable to launch
args list stdio Arguments for the subprocess
env mapping stdio Environment passed to the subprocess
url string HTTP Remote MCP endpoint
headers mapping HTTP Headers for remote server requests
enabled bool both Skip the server entirely when false
timeout number both Tool call timeout
connect_timeout number both Initial connection timeout
tools mapping both Filtering and utility-tool policy
auth string HTTP Authentication method. Set to oauth to enable OAuth 2.1 with PKCE
sampling mapping both Server-initiated LLM request policy (see MCP guide)

tools policy keys

Key Type Meaning
include string or list Whitelist server-native MCP tools
exclude string or list Blacklist server-native MCP tools
resources bool-like Enable/disable list_resources + read_resource
prompts bool-like Enable/disable list_prompts + get_prompt

Filtering semantics

include

If include is set, only those server-native MCP tools are registered.

tools:
  include: [create_issue, list_issues]

exclude

If exclude is set and include is not, every server-native MCP tool except those names is registered.

tools:
  exclude: [delete_customer]

Precedence

If both are set, include wins.

tools:
  include: [create_issue]
  exclude: [create_issue, delete_issue]

Result:

  • create_issue is still allowed
  • delete_issue is ignored because include takes precedence

Utility-tool policy

Hermes may register these utility wrappers per MCP server:

Resources:

  • list_resources
  • read_resource

Prompts:

  • list_prompts
  • get_prompt

Disable resources

tools:
  resources: false

Disable prompts

tools:
  prompts: false

Capability-aware registration

Even when resources: true or prompts: true, Hermes only registers those utility tools if the MCP session actually exposes the corresponding capability.

So this is normal:

  • you enable prompts
  • but no prompt utilities appear
  • because the server does not support prompts

enabled: false

mcp_servers:
  legacy:
    url: "https://mcp.legacy.internal"
    enabled: false

Behavior:

  • no connection attempt
  • no discovery
  • no tool registration
  • config remains in place for later reuse

Empty result behavior

If filtering removes all server-native tools and no utility tools are registered, Hermes does not create an empty MCP runtime toolset for that server.

Example configs

Safe GitHub allowlist

mcp_servers:
  github:
    command: "npx"
    args: ["-y", "@modelcontextprotocol/server-github"]
    env:
      GITHUB_PERSONAL_ACCESS_TOKEN: "***"
    tools:
      include: [list_issues, create_issue, update_issue, search_code]
      resources: false
      prompts: false

Stripe blacklist

mcp_servers:
  stripe:
    url: "https://mcp.stripe.com"
    headers:
      Authorization: "Bearer ***"
    tools:
      exclude: [delete_customer, refund_payment]

Resource-only docs server

mcp_servers:
  docs:
    url: "https://mcp.docs.example.com"
    tools:
      include: []
      resources: true
      prompts: false

Reloading config

After changing MCP config, reload servers with:

/reload-mcp

Tool naming

Server-native MCP tools become:

mcp_<server>_<tool>

Examples:

  • mcp_github_create_issue
  • mcp_filesystem_read_file
  • mcp_my_api_query_data

Utility tools follow the same prefixing pattern:

  • mcp_<server>_list_resources
  • mcp_<server>_read_resource
  • mcp_<server>_list_prompts
  • mcp_<server>_get_prompt

Name sanitization

Hyphens (-) and dots (.) in both server names and tool names are replaced with underscores before registration. This ensures tool names are valid identifiers for LLM function-calling APIs.

For example, a server named my-api exposing a tool called list-items.v2 becomes:

mcp_my_api_list_items_v2

Keep this in mind when writing include / exclude filters — use the original MCP tool name (with hyphens/dots), not the sanitized version.

OAuth 2.1 authentication

For HTTP servers that require OAuth, set auth: oauth on the server entry:

mcp_servers:
  protected_api:
    url: "https://mcp.example.com/mcp"
    auth: oauth

Behavior:

  • Hermes uses the MCP SDK's OAuth 2.1 PKCE flow (metadata discovery, dynamic client registration, token exchange, and refresh)
  • On first connect, a browser window opens for authorization
  • Tokens are persisted to ~/.hermes/mcp-tokens/<server>.json and reused across sessions
  • Token refresh is automatic; re-authorization only happens when refresh fails
  • Only applies to HTTP/StreamableHTTP transport (url-based servers)