Skip to main content
Glama
123,940 servers. Updated
Browse by product

Matching MCP tools:

Matching MCP Connectors:

"A tool or resource for improving prompt writing" matching MCP servers:

GET /v1/servers – MCP directory API reference
  • A
    license
    Not graded
    quality
    C
    maintenance
    An MCP server that allows agents to test and compare LLM prompts across OpenAI and Anthropic models, supporting single tests, side-by-side comparisons, and multi-turn conversations.
    MIT
  • A
    license
    Not graded
    quality
    D
    maintenance
    A local MCP server for prompt evaluation, enabling users to define test cases, run prompts against multiple LLM providers, score outputs with deterministic and LLM-graded assertions, and track quality over time, all within an AI coding environment.
    MIT
  • F
    license
    Not graded
    quality
    D
    maintenance
    A lightweight multi-provider MCP testing fixture with two providers (eva_air and uk_railway), each exposing 5 tools using in-memory fake data, designed for verifying MCP client tool discovery, tool calls, and multi-provider routing.
    -
  • A
    license
    Not graded
    quality
    D
    maintenance
    MCP-first A/B testing server that enables agents to manage experiments (create, update traffic splits, read results, apply winning variants) from tools like Claude Code, with self-hosted Cloudflare backend.
    MIT
  • A
    license
    A
    quality
    C
    maintenance
    A remote MCP server exposing 3 tools via Model Context Protocol: score_prompt (free, grades any LLM prompt A-F on 0-40 scale), optimize_prompt (returns optimized prompt + dimension breakdown, $0.025 USDC), and compare_models (Claude vs GPT-4o head-to-head, $1.25 USDC). Remote HTTP server at /api/mcp.
    2
    57 npm
    2
    MIT
  • A
    license
    A
    quality
    B
    maintenance
    Checks the outcome after an agent handoff, when a request, 200 or ack only shows the handoff. Reads one field of one exact public HTTPS JSON record, with a same-site known-good control, for 20-120 s. Returns PROVED, DISPROVED or INCONCLUSIVE with a signed receipt you can verify. 5 free checks, then USD 1 per completed check, by card (Stripe Checkout) or existing Link wallet. INCONCLUSIVE is free.
    10
    Apache 2.0
  • A
    license
    A
    quality
    B
    maintenance
    Zero-sidecar MCP server embedded directly in the Godot 4 editor as a GDScript EditorPlugin — no Node or Python sidecar. Reflection-driven tools over any engine class, validate-before-write GDScript, scene/script/resource authoring, and a runtime play-test loop (play, screenshot, input, assert).
    56
    51
    MIT
  • A
    license
    Not graded
    quality
    C
    maintenance
    Enables AI assistants to operate directly inside a running Unity Editor project, creating scenes, generating scripts, simulating input, capturing screenshots, inspecting performance, and automating editor tasks through its built-in tools and resources.
    MIT
  • A
    license
    Not graded
    quality
    C
    maintenance
    Enables AI agents to drive a local asset review loop: list and fetch paired original/output items (including image content for visual comparison), mark pass/reject/unsure with problem tags and region annotations, batch-review scoped selections, and export results as JSON or CSV. Also supports round archiving, detecting stale results after source re-renders, and listing previous-round rejects.
    1
    MIT
  • A
    license
    Not graded
    quality
    B
    maintenance
    Generates a pytest suite from acceptance criteria withheld from the coding agent, so the tests can disagree with the code; qikly_run never returns the criteria. The CLI also scores an existing suite by planting faults, and ships as an agent Skill (qikly --install-skill). Runs locally (uvx --from "qikly[mcp]" qikly-mcp): your code and API key stay on your machine.
    322 PyPI
    21
    Apache 2.0
  • A
    license
    Not graded
    quality
    B
    maintenance
    Exposes a fictional smart-home store's REST API to agents as schema-validated MCP tools, resources, and prompts, letting them search products, check inventory, place atomic orders, look up customers and orders, and open support tickets. It also adds auth injection, rate limiting, REST-to-MCP error mapping with actionable hints, per-call JSONL tracing, and a golden-task eval harness for tool selection and argument correctness.
    MIT
  • A
    license
    A
    quality
    B
    maintenance
    Audits local package folders to generate publish-readiness reports and previews of NPM tarball contents. It helps developers identify and resolve configuration issues like missing types or broken exports before releasing code.
    3
    71 npm
    MIT
  • A
    license
    A
    quality
    C
    maintenance
    A reference MCP server that enforces identity-aware tool access using role-based permissions (Reader, Analyst, Auditor) and supports multiple identity routes like Entra RBAC, Copilot Studio, and Okta XAA. It provides read-only access to test evidence with explicit denial paths for unauthorized tools.
    7
    MIT
  • A
    license
    Not graded
    quality
    B
    maintenance
    A deliberately hostile MCP server that serves poisoned tool metadata, a rug-pull tool, a result-injection tool, a poisoned resource and a poisoned prompt so that tool-list changes and metadata-based attacks can be demonstrated against a client. It runs fully offline with an inert victim, letting users compare a pinned client against an ungoverned one and see where defences must sit.
    MIT
  • A
    license
    Not graded
    quality
    B
    maintenance
    Enables developers to build production-grade MCP services with dependency injection, zero global state, layered imports, and a sample user-notes tool, resource, and prompt. It includes Testcontainers, Prometheus metrics, Kubernetes probes, and structured logging for testable local and production deployments.
    MIT
  • A
    license
    Not graded
    quality
    D
    maintenance
    Instrumented MCP server for testing client conformance to list_changed notifications, enabling verification of dynamic tool, resource, and prompt surfacing.
    MIT
  • A
    license
    A
    quality
    C
    maintenance
    Enables coding agents to verify whether a GitHub pull request is genuinely ready by checking draft state, conflicts, check results on the head commit, review requirements, merge queue status, and expected commit, returning a verdict with reasons and owners pinned to a commit and timestamp. It reports merged or closed PRs without judging them and never authorizes a merge.
    1
    MIT
  • A
    license
    A
    quality
    B
    maintenance
    Read-only data patrol for AI agents: finds broken partitions in DuckDB, CSV or Parquet tables, verifies each proposed fix against source control totals on a copy, and escalates anything it cannot prove to a person.
    6
    840 PyPI
    5
    MIT
  • A
    license
    A
    quality
    B
    maintenance
    MCP server exposing statistical regression testing for LLM agents as a "run" tool: p-value, effect size, and confidence interval on whether agent behavior actually changed.
    1
    113 PyPI
    Apache 2.0
  • A
    license
    A
    quality
    B
    maintenance
    Fail-closed merge gate for AI coding agents: verify_repo runs the tests that existed before the change against a git working tree and answers MERGE, BLOCK or INCONCLUSIVE. The agent names what to judge; the operator pins the baseline and the floors.
    2
    61 PyPI
    4
    AGPL 3.0
  • A
    license
    A
    quality
    C
    maintenance
    Enables AI agents to hire real human operators for tasks requiring physical presence, human perception, or judgment, such as verification, testing, data collection, and physical-world tasks.
    4
    59 npm
    1
    MIT
  • A
    license
    A
    quality
    D
    maintenance
    A deterministic preflight checker for outbound SMS/iMessage that catches silent filtering, segment blowups, and dropped iMessage features before sending.
    1
    43 npm
    1
    MIT
  • A
    license
    A
    quality
    A
    maintenance
    Measures what MCP servers cost in context tokens: probes a URL or a local command now, measures a whole config file, and looks up the daily results for every server in the official MCP registry on mcpcost.ulehla.dev.
    6
    3
    MIT