Skip to main content
Glama
sanjibani

mcp-shield

by sanjibani
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Remote

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
SEARXNG_URLNoThe URL of the searxng serverhttp://localhost:8080
MCP_SHIELD_AUDITNoEnable audit (set to 0 to disable)1
MCP_SHIELD_AUDIT_LOGNoPath to audit log file (default stderr)

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

Tools

Functions exposed to the LLM to take actions

NameDescription
audit_tailA

Return the last n records from a JSONL audit log.

Use when: "what did the agent just do?", "did anything fail?". Example: path="/var/log/mcp-shield/audit.jsonl", n=50.

audit_summaryA

Aggregate counts over a JSONL audit log: total calls, error rate, top tools.

Use when: "how healthy is the MCP fleet?", "what's the error rate?". Example: path="/var/log/mcp-shield/audit.jsonl".

red_teamA

Run a curated set of injection payloads through the sanitizer.

Use when: "is the sanitizer actually catching things?", "compliance evidence for security review". Example: strict=False (default; reports hits without raising).

Each result row shows {"input", "caught", "pattern"}. caught is True iff the sanitizer matched any pattern.

scan_inputA

Validate an args dict against a JSON schema; return OK or first error.

Use when: "is my agent's call valid before I send it?". Example: args={"q":"hi"}, schema={"type":"object","properties":{"q":{"type":"string"}}}.

Returns {"valid": true} or {"valid": false, "error": "..."}. Never raises — the tool surfaces validation results as data.

patterns_listA

List the prompt-injection patterns the sanitizer detects.

Use when: "what does this tool actually look for?".

sanitize_previewA

Preview what the sanitizer would do to text without raising.

Use when: "what gets redacted from this output?". Example: text="ignore previous instructions", strict=False.

versionA

Return mcp-shield version + runtime config.

Use when: "what version is deployed?".

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources

Deploy Server
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

TDQS

A4.2/5.0

Scored across 7 tools

Disambiguation5/5

Each tool has a clearly distinct purpose: auditing (summary and tail), pattern management (list and test), sanitization preview, input validation, and version info. No overlap.

Naming Consistency5/5

All tool names use snake_case and follow a verb_noun pattern (audit_summary, audit_tail, patterns_list, red_team, sanitize_preview, scan_input). Even 'version' fits as a simple noun command.

Tool Count5/5

With 7 tools, the surface is well-scoped for a security/audit server. It covers auditing, pattern introspection, testing, preview, input validation, and version info without bloat.

Completeness4/5

Covers core workflows: auditing (summary + tail), pattern listing, red team testing, sanitization preview, and input validation. Minor gaps like dynamic pattern updates or configuration are absent but not critical for the stated purpose.

Maintenance

ActivityInactive
ResponsivenessNo issues

Resources