fastmcp-gateway
OfficialServer Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| LOG_LEVEL | No | Logging level | INFO |
| GATEWAY_HOST | No | Bind address | 0.0.0.0 |
| GATEWAY_NAME | No | Server name | fastmcp-gateway |
| GATEWAY_PORT | No | Bind port | 8080 |
| GATEWAY_CODE_MODE | No | Enable the experimental `execute_code` meta-tool (see Code Mode) | false |
| GATEWAY_UPSTREAMS | Yes | JSON object: {"domain": "url", ...} or {"domain": {"url": "...", "allowed_tools": [...], "denied_tools": [...]}} (see Access Control) | |
| GATEWAY_HOOK_MODULE | No | Python module path for execution hooks: module.path:factory_function | |
| GATEWAY_INSTRUCTIONS | No | Custom LLM system instructions | Built-in |
| GATEWAY_REFRESH_INTERVAL | No | Seconds between automatic registry refresh cycles | |
| GATEWAY_UPSTREAM_HEADERS | No | JSON object: {"domain": {"Header": "Value"}, ...} | |
| GATEWAY_REGISTRATION_TOKEN | No | Shared secret for dynamic registration endpoints (see below) | |
| GATEWAY_DOMAIN_DESCRIPTIONS | No | JSON object: {"domain": "description", ...} | |
| GATEWAY_REGISTRY_AUTH_TOKEN | No | Bearer token for upstream discovery | |
| GATEWAY_CODE_MODE_MAX_MEMORY | No | Per-run heap memory cap (bytes) for `execute_code` | 268435456 |
| GATEWAY_CODE_MODE_AUDIT_VERBATIM | No | Emit raw code body at DEBUG in audit logs (PII-sensitive) | false |
| GATEWAY_CODE_MODE_MAX_ALLOCATIONS | No | Per-run allocation cap for `execute_code` | 10000000 |
| GATEWAY_CODE_MODE_MAX_NESTED_CALLS | No | Max number of upstream tool calls one `execute_code` run may make | 50 |
| GATEWAY_CODE_MODE_MAX_DURATION_SECS | No | Per-run wall-clock cap for `execute_code` | 30 |
| GATEWAY_CODE_MODE_MAX_RECURSION_DEPTH | No | Per-run stack depth cap for `execute_code` | 200 |
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
Server capabilities have not been inspected yet.
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
No tools | |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
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/Ultrathink-Solutions/fastmcp-gateway'
If you have feedback or need assistance with the MCP directory API, please join our Discord server