"Tools for slow thinking, step-back reasoning, and contextual memory capabilities" matching MCP servers:

Enables multiple AI agents to hand off verified work packages—such as skills, lemmas, datasets, and patches—by publishing, searching, pulling, and locally re-verifying them without sharing context.

Exposes six evidence-oriented tools over stdio so MCP clients can navigate unfamiliar code, ask typed questions about repository evidence, review completed changes, and select existing tests.

Enables generating JSON Schema from sample data, generating TypeScript types, validating data against schemas, creating mock data from schemas, and comparing schemas for differences.

Webhook management and testing tools for AI agents. Provides tools for sending, validating, generating, and debugging webhooks.

Enables building and evaluating LangGraph agents over a protocol-level MCP server to measure failure rates across four agent topologies.

Enables validating JSON/JSONC, getting/setting values with jq-like paths, pretty-printing or minifying, validating against Ajv JSON Schema, and diffing local files or inline strings without network calls.

Enables validating IFC models against IDS requirements with coverage reporting, auditing LOD by project stage, and extracting quantity take-offs, including combined audit summaries and full BIM health checks. It exposes these capabilities as MCP tools for Claude Desktop, producing Excel, HTML, and BCF reports.

Enables coding agents to run Playwright e2e tests, validate Supabase RLS policies with role-based SQL, typecheck TypeScript, execute npm scripts with parsed test output, and validate Next.js builds, all through a structured MCP interface.

Enables AI agents to run configured test suites, inspect failures and logs, compare runs, and draft or file bug reports only after human confirmation, with safeguards such as selector validation, environment isolation, timeouts, and redaction.

MCP server providing code review, auto-fix, test running, linting, formatting, and refactor suggestions for Claude Code.

Enables AI agents to interact with Ethereum smart contracts through Anvil, providing capabilities to read Solidity code, simulate and execute transactions, manipulate blockchain state, query events, and test contracts in isolated environments for development and auditing workflows.

Provides 32 remote tools that let agents validate common data formats, optimize or minify code and content, and generate synthetic test data such as fake records, IDs, and passwords.

Provides a hand-written MCP server integrated with a LangGraph agent to benchmark multiple agent topologies and measure their failure rates.

Code linting and style checking tools for AI agents, exposed as an MCP server. Supports style checks, naming conventions, complexity analysis, dead code detection, and import analysis.

Bridges AI agents with VS Code's debugger, enabling breakpoint management, step execution, variable inspection, and stack tracing via CLI commands.

Provides AI agents with web accessibility analysis tools via MCP, enabling checks for alt text, heading hierarchy, color contrast, ARIA validation, and form accessibility.

Enables users to list and inspect household memory-conflict tasks, score answers, run evaluations, and retrieve provenance data through MCP tools.

Enables AI agents and test runners to control Android devices via local ADB, including listing devices, tapping, swiping, typing, sending system keys, launching apps, and dumping UI hierarchy. Communicates over MCP stdio without exposing network listeners.

Enables Playwright QA automation with a custom Memory MCP that provides tiered retention and mortgage compliance audit, allowing AI agents to remember flakiness history and journey maps while adhering to data privacy and audit requirements.

Enables AI agents to safely read, search, and inspect a local git repository, including PR-style diffs and changed-file summaries. It also supports opt-in allowlisted test runs.

Enables an agent to build and reuse a persistent library of tested scripts, listing and running saved helpers and saving new ones only after their tests pass.

Persistent visual cache for LLM-driven software development. Caches screenshots using perceptual hashing, vector search, and AX trees to prevent token overhead and visual hallucination loops.

An MCP server that complements Epic's official Unreal Engine MCP server with 78 additional tools across 14 subsystems for build/cook/package, cinematics, Niagara, automation testing, source control, profiling, World Partition, and project maintenance, using Unreal's built-in Python and Remote Control plugins.

A deterministic verification gate for MCP clients that independently checks model outputs against evidence, contradictions, calibration, and provenance without relying on LLM self-assessment.

Enables deterministic behavioral regression review of pull-request diffs by checking changed code against approved incident-derived contracts. It exposes read-only tools to assess diffs and pull requests, list and fetch contracts, and report outcomes over stdio without mutating repositories.

Enables AI agents to interact with 1C: Enterprise development environment, including running tests, managing launch profiles, building configurations, and performing database operations through the 1C: Platform Tools extension.

A Model Context Protocol (MCP) server that provides testing and debugging tools for Stripe integrations, including test clock management, customer and product management, and subscription testing.

Enables LLMs to interact directly with generated REST services by discovering and invoking CRUD tools and reading exposed resources for list and get-by-id data.

Provides FHIR resource validation, synthetic test fixture generation, and HIPAA-safe logging review as MCP tools for AI agents.

Enables statistical analysis through three tools—survival analysis, paired significance testing, and distribution drift detection—plus a harness to evaluate quality, latency, and cost.