Provides tools for executing parameterized SQL queries, catalog discovery, CRUD operations, and connection management with TLS support for PostgreSQL databases.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@SentryFrogg MCP Server show tables in profile mydb"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Field | Value |
Product | SentryFrogg MCP Server |
Version | 4.2.0 |
Runtime | Node.js ≥ 16 |
Interfaces | Model Context Protocol (PostgreSQL · SSH · HTTP) |
License | MIT |
Related MCP server: connect
SentryFrogg MCP Server supplies a governed command plane for MCP-compatible agents that operate data platforms, remote shells and web services. The implementation prioritises deterministic behaviour, encrypted credential storage and prescriptive workflows so that autonomous agents can execute infrastructure tasks with enterprise auditability.
Capability | Detail |
PostgreSQL control | Parameterised SQL, catalog discovery, CRUD helpers, mutual TLS, connection profiling. |
SSH execution | Serial command dispatch per profile, password/key authentication, reachability diagnostics. |
HTTP access | REST verbs with JSON payloads, health checks, programmable headers and bearer tokens. |
Secret vault | AES-256 encrypted profiles persisted in |
Telemetry | Tool-level statistics via |
Component | Scope |
| MCP entry point, tool catalogue, lifecycle supervision. |
| Service registration, dependency wiring, resource cleanup. |
| SQL execution, profile validation, TLS configuration, pool management. |
| SSH sessions, sequential execution enforcement, profile hygiene. |
| HTTP invocation, header synthesis, response shaping. |
| Encrypted persistence and retrieval of profile objects. |
| Key lifecycle, cryptographic primitives, payload size guards. |
| Canonical validation for incoming payloads. |
mcp_psql_managerAttribute | Specification |
Required flow |
|
Actions |
|
Credentials | Either discrete fields ( |
TLS options |
|
Query rules |
|
Response format | JSON with |
Rejection triggers | Missing profile, malformed SQL, payload limits exceeded, invalid TLS configuration. |
mcp_ssh_managerAttribute | Specification |
Required flow |
|
Actions |
|
Execution model | Commands trimmed and length-limited; pipes/redirects permitted; per-profile execution is strictly sequential. |
Outputs | JSON containing |
Security posture | Secrets encrypted at rest; no templating—agents must supply fully qualified commands. |
mcp_api_clientAttribute | Specification |
Actions |
|
Inputs |
|
Behaviour | Local and private addresses allowed; HTTP status/body returned in structured JSON; transport or parsing failures emit MCP internal errors. |
Invoke setup_profile to persist credentials and TLS artefacts; secrets encrypt with AES-256 using .mcp_profiles.key (0600 permissions).
Reference the same profile_name for subsequent operations; omitted sensitive fields inherit stored encrypted values.
Rotate credentials by reissuing setup_profile; the latest payload supersedes previous entries.
Audit existing profiles via list_profiles; responses never disclose secrets.
Retire unused profiles by editing profiles.json under change control.
Prefer embedding sslmode directives in connection_url; explicit payload fields override URL parameters.
Keep ssl_reject_unauthorized at true unless communicating with trusted self-signed endpoints.
Provide ssl_servername whenever certificate CN/SAN mismatches the host.
Supply PEM blocks as single-line strings using \n escape sequences; leading/trailing spaces are disallowed.
ssl_passphrase must be non-empty if provided; omit otherwise.
Task | Command |
Clone and install |
|
Syntax check |
|
Launch (stdio) |
|
Update dependencies |
|
Reset profile store | Remove |
Encryption key lifecycle: .mcp_profiles.key generated on first run; override via ENCRYPTION_KEY for coordinated environments.
Secret exposure: MCP responses never include decrypted values; rotation requires explicit setup_profile.
Input governance: SQL statements, SSH commands and HTTP payloads are length-limited; oversized inputs are rejected pre-execution.
Audit trail: stderr logging captures timestamped events per tool to support collection by SIEM platforms.
Dependency governance: locked versions of pg, ssh2, node-fetch, @modelcontextprotocol/sdk; monitor advisories for patch cadence.
Symptom | Diagnostic Actions | Remediation |
PostgreSQL TLS failure | Inspect | Update TLS materials; rerun |
SSH command hang | Validate command length, ensure non-interactive execution, check remote prompts. | Adjust command or script; rerun |
HTTP error response | Review returned status/body, verify | Correct payload; retry request. |
Missing profile | Execute | Recreate via |
Consult CHANGELOG.md for a dated record of functional and operational updates, including TLS support and renaming.
Submit changes through pull requests accompanied by verification evidence (npm run check).
Never commit .mcp_profiles.key or environment-specific secrets.
Use maintainer contact information in package.json for escalation or integration assistance.
HTTP caller. Fields: action ∈ {get, post, put, delete, patch, check_api}, url (required), data (JSON body for mutating verbs), headers (string map), auth_token (prefixed into Authorization unless headers.Authorization supplied). Local URLs allowed. Responses are structured results or MCP errors.
Inputs: action (required), url, data, headers, +1 more.
PostgreSQL toolchain. Flow: setup_profile → action. setup_profile accepts credentials or connection_url plus optional TLS (ssl_mode, ssl_ca, ssl_cert, ssl_key, ssl_passphrase, ssl_servername, ssl_reject_unauthorized); secrets stored encrypted. Subsequent calls reuse profile_name: quick_query (adds LIMIT 100 if absent; supports params array for $ placeholders), show_tables, describe_table, sample_data, database_info, insert_data, update_data, delete_data, list_profiles.
Inputs: action (required), profile_name, connection_url, host, +18 more.
SSH executor. setup_profile stores host credentials (password or PEM private_key with optional passphrase); data encrypted. list_profiles enumerates profiles, system_info returns collected facts, check_host validates reachability, execute runs one trimmed command (pipes/redirects allowed) sequentially per profile; no concurrent runs.
Inputs: action (required), profile_name, host, port, +7 more.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Scored across 3 tools
Each tool targets a completely distinct domain: HTTP API calls, PostgreSQL database management, and SSH remote execution. There is no overlap in purpose or functionality, so an agent can clearly differentiate them.
All tool names follow the pattern 'mcp_<domain>_<role>' (e.g., mcp_api_client, mcp_psql_manager, mcp_ssh_manager), using consistent snake_case and a descriptive prefix. The variation between 'client' and 'manager' is appropriate for their roles.
With only three tools, the server covers three broad areas (API, database, SSH). While each tool is rich in sub-actions, the raw count is at the low end of the range, making it borderline but acceptable for a general-purpose server.
Within the declared domains, the tools provide comprehensive coverage: HTTP client supports all methods, PostgreSQL manager includes full CRUD and schema inspection, SSH manager handles command execution and system info. Minor gaps like bulk operations exist but do not hinder core workflows.
Governed MCP gateway: one endpoint for your tools, with credential custody and audit log.
Manage remote servers, SSH terminals, files, databases and proxies with scoped access and approvals.
MCP server for mandates, delegation, policy-gated execution, credential grants, and audit.
Hosted remote MCP for protected account access, permissions, activity history and supported undo.