Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
MCP_WARDEN_APPROVAL_TRANSPORTNoOverride the approval transport at runtime. Valid values: telegram, desktop, tui.

Instructions

Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.

This server publishes no instructions, or was last inspected before Glama recorded them.

Capabilities

Features and capabilities supported by this server

Protocol revision2025-11-25

CapabilityDetails
tools
{}

Tools

Functions exposed to the LLM to take actions

NameDescription
db_queryA

Run a NAMED QUERY against a database preset (PostgreSQL, MySQL, or Redis). You supply query_name (must match one declared in the preset) and params (positional). The SQL / command is FIXED at preset definition time — you cannot send arbitrary SQL. Returns rows as JSON. Approval prompt fires per the preset's policy. If the user previously approved a time-boxed window for this preset+action, the call proceeds without a new prompt and is recorded as 'windowed' in the audit log.

get_secret_for_envA

Reveal the raw secret value bound to a name. ALWAYS prompts for approval, regardless of preset policy. Prefer proxy_http — only use this if a child process you are about to spawn must read the secret from an environment variable (e.g. terraform apply reading AWS_SECRET_ACCESS_KEY). The returned value MUST NOT be quoted back into your reasoning trace.

list_presetsA

List available mcp-warden presets — named, scoped actions you may invoke. Returns name, description, type (http|ssh), and approval policy (auto|prompt|deny). Read-only; never returns secret values. Use proxy_http for HTTP actions and get_secret_for_env only as a last resort when a child process must read a secret from its environment.

proxy_httpA

Make an HTTP request through a preset. The preset selects the base URL and authentication; you supply path, method, and optional body / query. Allow-listed methods and paths are validated server-side BEFORE any credential is injected. Sensitive presets trigger a desktop / TUI approval prompt; you cannot bypass approval. If the user previously approved a time-boxed window for this preset+action, the call proceeds without a new prompt and is recorded as 'windowed' in the audit log. Every call is recorded to a local audit log.

sftp_transferA

Transfer a file between the preset's SSH host and the local machine. direction must be "get" (download) or "put" (upload). The remote path must match the preset's sftp_allowed_paths prefixes; the local path must be under $HOME or /tmp. Always key-based auth, host-key verified. If the user previously approved a time-boxed window for this preset+action, the call proceeds without a new prompt and is recorded as 'windowed' in the audit log.

ssh_execA

Run a shell command on the preset's SSH host. The command must match one of the preset's allowed_commands regexes (anchored ^...$). Returns stdout, stderr, and exit_code. Key-based auth only; host key is verified against the user's known_hosts file. Sensitive presets trigger the approval prompt. If the user previously approved a time-boxed window for this preset+action, the call proceeds without a new prompt and is recorded as 'windowed' in the audit log. Every call is recorded to the audit log.

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources

TDQS

A4.1/5.0

Scored across 6 tools

Disambiguation5/5

Each tool targets a distinct channel or resource: preset discovery (list_presets), HTTP (proxy_http), SSH command exec (ssh_exec), file transfer (sftp_transfer), named DB queries (db_query), and raw secret exposure (get_secret_for_env). The descriptions even explicitly steer callers (e.g., prefer proxy_http over get_secret_for_env), leaving little room for misselection despite shared 'preset' framing.

Naming Consistency3/5

All names are snake_case and readable, but conventions are mixed: two verb-first names (get_secret_for_env, list_presets) versus four resource/channel-first names (proxy_http, db_query, ssh_exec, sftp_transfer). The inconsistency is mild but predictable patterns are absent.

Tool Count5/5

Six tools map cleanly onto the server's scope: one discovery tool, four execution channels (HTTP, SSH, SFTP, DB), and one escape-hatch secret reader. Nothing feels padded or missing at the count level.

Completeness3/5

The execution surface is solid, but several referenced concepts have no corresponding tools: the audit log is written to on every call yet unreadable, and time-boxed approval windows are described but cannot be requested or inspected. Preset creation/editing is arguably omitted by design, but the observability gaps are notable dead ends.

Maintenance

ActivityMaintained
ResponsivenessNo issues