Skip to main content
Glama
iris-eval

iris-eval/mcp-server

by iris-eval
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Hybrid

Related Servers

Alternatives to iris-eval/mcp-server

No user-submitted related servers found.

    Related Servers

    • guardrails-mcp-server

      ExpertVagabond
      A
      license
      Not graded
      quality
      B
      maintenance
      MCP server for AI agent security guardrails. Provides input validation, prompt injection detection, PII redaction, output filtering, policy enforcement, rate limiting, and comprehensive audit logging.
      31 npm
      1
      MIT

    • mcp-context-inspector

      sohaibsohail98
      A
      license
      A
      quality
      A
      maintenance
      An MCP server that records agent execution metrics and exposes a Context Window Explorer to visualize exactly what entered the model's context window across sessions, tokens, and tool calls.
      8
      3
      MIT

    • WhitePact

      Guruprasath-Annadurai
      A
      license
      A
      quality
      A
      maintenance
      An MCP server that exposes governance, trust-scoring, compliance, guardrail, cost, drift, and supply-chain scanning tools and resources to any MCP client over stdio, Streamable HTTP, or legacy HTTP+SSE. It lets agents route every tool call through a deterministic five-way decision (allow, redact, require approval, deny, or quarantine) with hash-chained evidence, human approval workflows, and in-agent trust gates for LangChain, LangGraph, and Google ADK.
      30
      48 PyPI
      2
      MIT

    • runmeter

      Aptica-Solutions
      A
      license
      A
      quality
      B
      maintenance
      An MCP server that provides cost and reliability observability for LLM and agent workflows. It records model calls and allows querying and aggregating telemetry data through MCP tools.
      6
      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

    A4.8/5.0

    Scored across 9 tools

    Disambiguation5/5

    Each tool targets a distinct resource and action: traces are logged, queried, deleted; evaluations are either deterministic or LLM-judge based, with citation-specific analysis separate; rules are listed, deployed, and deleted. No two tools appear to do the same thing, and the boundary between evaluate_output and evaluate_with_llm_judge is clearly drawn.

    Naming Consistency5/5

    All tool names follow a consistent verb_noun snake_case pattern: log_trace, delete_trace, get_traces, list_rules, deploy_rule, delete_rule, evaluate_output, evaluate_with_llm_judge, verify_citations. Even longer names retain the pattern, and there is no mixing of styles or vague verbs.

    Tool Count5/5

    With 9 tools, the server is well-scoped. Each tool covers a necessary operation for the agent evaluation domain, and there is no bloat or redundancy. The count feels appropriate for the complexity of the domain, fitting the ideal 3-15 range.

    Completeness5/5

    The tool surface covers the full lifecycle: trace creation, retrieval, deletion; two complementary evaluation paths (deterministic and LLM-based) plus citation verification; rule deployment, listing, and deletion. There are no obvious dead ends or missing operations for the stated purpose of storing and evaluating agent executions.

    Maintenance

    ActivityActive
    ResponsivenessUnresponsive

    Resources