mcp-diet
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| --deny | No | Remove matching tool names or wildcard patterns (e.g. delete_*,drop_*). | |
| --allow | No | Allow only matching tool names or wildcard patterns (e.g. get_*,list_*). | |
| --max-desc | No | Deterministically truncate tool and property descriptions to the given number of characters. | |
| --read-only | No | Keep only read-only tools (annotations.readOnlyHint or read-only heuristic). Set to "true" to enable. | false |
| --spill-dir | No | Custom directory for spilled oversized tool outputs. | |
| --max-result-kb | No | Spill oversized tools/call results to a temp file when they exceed this size in KB. | 512 |
| --redact-secrets | No | Redact leaked API keys, PATs, and credentials in tools/call output. Set to "true" to enable. | false |
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
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"listChanged": false
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| mcp_diet_analyze_toolsB | Analyze an array of MCP tool definitions and compute deterministic tree-shaking byte and token savings under mcp-diet policies. |
| mcp_diet_read_spillA | Safely read a bounded slice from an oversized mcp-diet spill file by 1-based line range, UTF-8 byte offset, or RFC 6901 JSON Pointer. |
| mcp_diet_redact_textA | Redact leaked API keys, GitHub PATs, AWS keys, connection URL passwords, bearer tokens, and private keys from text. |
| mcp_diet_statusA | Inspect the active mcp-diet runtime firewall configuration, version, and crash-guard thresholds. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 4 tools
Each tool maps to a clearly different action: analysis of tool definitions, reading spill files, redacting secrets, and inspecting runtime status. There is no plausible overlap — an agent can pick the right tool from the name alone, and the descriptions reinforce distinct resource/action pairs.
All four tools share the `mcp_diet_` server prefix followed by a snake_case verb_noun pattern (analyze_tools, read_spill, redact_text, status). The one slight deviation is `status` (noun-only), but it is unambiguous and predictable within the set.
Four tools is well-scoped for a narrow utility server covering analysis, spill reading, redaction, and status. It is on the thin side — the surface could support a policy/configuration tool — but no tool feels redundant or out of place.
The lifecycle is largely covered: analyze computes savings, read_spill retrieves oversized output, redact_text handles secret leakage, and status reports runtime config. The main gap is the absence of a tool to set or apply mcp-diet policies/config, so agents can inspect and analyze but not mutate configuration.