Skip to main content
Glama
DeployFaith

hermes-gpt

by DeployFaith
OverviewSchemaRelated ServersScoreDiscussions
Python
Local

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
HERMES_GPT_OWNER_ACKNoMust equal 'I_UNDERSTAND_THIS_CAN_MUTATE_MY_MACHINE' for owner tools (default: unset).
HERMES_GPT_ENABLE_WRITENoSet to '1' to enable write file and patch tools (default: unset, hidden).
HERMES_GPT_OPERATOR_LEVELNoOperator level: read_only, cron, skills, skills_config, workspace, owner (default: read_only).
HERMES_GPT_ENABLE_TERMINALNoSet to '1' to enable terminal command execution (default: unset, hidden).
HERMES_GPT_OPERATOR_ENABLEDNoSet to '1' to enable operator mode (default: unset, false).
HERMES_GPT_ENABLE_MEMORY_WRITENoSet to '1' to enable memory add, replace, remove actions (default: unset, disabled).
HERMES_GPT_OPERATOR_APPLY_MODENoApply mode: dry_run or direct (default: dry_run).
HERMES_GPT_UNSAFE_REMOTE_NOAUTHNoSet to '1' to bypass remote profile block for unsafe experiments (default: unset).
HERMES_GPT_ENABLE_SESSION_SEARCHNoSet to '1' to enable session search tool (default: unset, hidden).
HERMES_GPT_OPERATOR_DENIED_PATHSNoExtra denied paths (additions only, cannot weaken defaults; default: built-in).
HERMES_GPT_OPERATOR_ALLOWED_PATHSNoComma-separated workspace root paths; empty disables workspace writes (default: empty).
HERMES_GPT_OPERATOR_ALLOWED_PROFILESNoComma-separated profile names allowed, or '*' for all (default: default).

Capabilities

Features and capabilities supported by this server

CapabilityDetails
tools
{
  "listChanged": false
}
prompts
{
  "listChanged": false
}
resources
{
  "subscribe": false,
  "listChanged": false
}
experimental
{}

Tools

Functions exposed to the LLM to take actions

NameDescription
hermes_read_fileD–
hermes_search_filesD–
hermes_memoryD–
hermes_skill_listD–
hermes_skill_viewD–
hermes_operator_policyA

Return the current operator policy summary. Read-only. Never secrets.

hermes_operator_statusA

Return operator runtime status. Read-only. Never secrets.

hermes_operator_audit_tailA

Return the last limit audit records. Read-only.

hermes_operator_doctorC

Run a read-only health check across operator surfaces.

hermes_operator_snapshotC

Return a single current-state summary of the operator.

hermes_release_doctorC

Check whether the repo/operator is safe to ship.

hermes_operator_recoverC

Conservative recovery sequence. Dry-run by default.

hermes_cron_listD–
hermes_cron_statusD–
hermes_cron_runD–
hermes_cron_pauseD–
hermes_cron_copyD–
hermes_cron_moveD–
hermes_skill_diffD–
hermes_skill_createD–
hermes_skill_editD–
hermes_skill_patchD–
hermes_skill_write_fileD–
hermes_skill_copyD–
hermes_skill_sync_to_defaultD–
hermes_skill_deleteD–
hermes_config_getD–
hermes_config_setD–
hermes_config_patchD–
hermes_env_statusD–
hermes_env_set_nonsecretD–
hermes_env_copy_nonsecretD–
hermes_gateway_statusD–
hermes_gateway_restartD–
hermes_workspace_readD–
hermes_workspace_patchD–
hermes_workspace_write_fileD–
hermes_workspace_run_testD–
hermes_git_statusD–
hermes_git_diffD–
hermes_owner_run_commandD–
hermes_owner_patchD–
hermes_owner_write_fileD–

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/DeployFaith/hermes-gpt-bridge'

If you have feedback or need assistance with the MCP directory API, please join our Discord server