Skip to main content
Glama
Sign In
@altirs/mcp-server

@altirs/mcp-server

by altirs
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Remote

Related Servers

Alternatives to @altirs/mcp-server

No user-submitted related servers found.

    Related Servers

    • genpark-agent-prompt-injection

      Alpha-Park
      A
      license
      Not graded
      quality
      Not graded
      maintenance
      Lets MCP-compatible assistants vet inbound prompts and untrusted text for instruction-override manipulation, separator escapes, and concealed encodings before processing them. Additional inline controls cover spending limits, repetitive-plan interruption, unsafe host-action denial, and output sanitization without third-party libraries.
      1
      MIT

    • genpark-agent-prompt-injection

      alphaparkinc
      A
      license
      Not graded
      quality
      B
      maintenance
      Enables MCP clients and autonomous agents to screen incoming prompts for system overrides, delimiter breakouts, and encoded payload evasion, helping block prompt injection and jailbreak attempts before execution.
      8
      MIT

    • toolwall

      kalpitphogat
      A
      license
      Not graded
      quality
      C
      maintenance
      Enables AI agents to use upstream MCP tools safely by scanning every tool result for indirect prompt injection and allowing, fencing as untrusted data, or blocking it while logging audit events.
      MIT

    • shipcheck-mcp

      noureldeensalama
      A
      license
      Not graded
      quality
      B
      maintenance
      Enables MCP-compatible AI agents to scan code for leaked secrets, copyleft licenses, unprotected routes, missing privacy policies, and risky card handling before committing or shipping.
      86 npm
      MIT
    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

    A4.3/5.0

    Scored across 5 tools

    Disambiguation4/5

    check_content is a composite that overlaps with detect_pii, scan_injection, and check_safety, but its description clearly positions it as the default all-in-one gate, while the individual tools are for targeted use. check_hallucination is distinct because it requires source context.

    Naming Consistency4/5

    Most tools follow a verb_noun pattern (check_content, detect_pii, scan_injection, check_safety, check_hallucination). scan_injection deviates slightly from the check_* prefix used by the other three check tools, but the pattern is still readable and predictable.

    Tool Count5/5

    Five tools is a well-scoped set for a content-safety server. Each tool covers a distinct safety engine, with check_content serving as the umbrella entry point and the others providing focused checks.

    Completeness4/5

    The server covers the main guardrail categories: safety, PII, injection, and hallucination. A minor gap is the lack of a dedicated tool for updating or managing guardrail configurations, but the core detection surface is complete for its stated purpose.

    Maintenance

    ActivitySlowing
    ResponsivenessNo recent community issues

    Resources