Evaluation

Everything here was classified as evaluation by keyword match against the maintainer's own description, so treat the grouping as a starting point rather than a verdict.

The list is ordered by the most recent commit, not by stars. A popular project that stopped in 2024 is not a better answer than a smaller one shipped last week.

Listed, not yet verified by us (60)

Published to the registry, but we have not yet checked its repository. Treat the entry as the maintainer’s claim only.

io.github.Siddhukaushik/slimdex-mcp — v1.0.0
Narrow code retrieval for agents: outlines, symbol context, dep graph, persistent memory.
io.github.sind00/flippa-mcp — v1.0.2
Search, analyze, and evaluate online businesses for sale on Flippa.com marketplace.
EzBiz Business Intelligence — v1.0.0
AI business intelligence: competitor analysis, web scoring, reviews, market research
io.github.Skitchy/rekindle — v0.2.1
MCP session continuity engine. Boot reports, orientation scoring, and end-session capture. SQLite.
M3 Memory — v2026.7.31.1
Local-first memory — 100+ tools, 99.2% LongMemEval-S retrieval@10, hybrid search, GDPR, no cloud.
io.github.smythmyke/govtoolspro-mcp-server — v0.1.3
Workflow tools for federal contractors: go/no-go scoring, incumbent intel, recompete, NECO.
io.github.SpaceFrontiers/mcp — v0.3.0
Citable retrieval across papers, books, patents, Wikipedia, and live social sources.
rmbr — v0.2.0
Embedded, local-first memory and retrieval for AI agents. One SQLite file, no server, no API key.
Hive Agent Kyc — v1.0.0
KYA agent identity verification and trust scoring for autonomous A2A networks
HiveAudit Readiness — v1.0.0
Multi-jurisdictional AI compliance readiness scoring with sourced penalty math.
Hive Credit — v1.0.0
Agent credit issuance and scoring — programmable credit lines on Base L2
Hive Evaluator — v1.1.0
MCP server: NEED + YIELD + CLEAN-MONEY gates with EIP-3009 attestations · Hive Civilization
Hive Gateway — v1.2.0
Unified gateway hosting 5 Hive Civilization MCP servers (evaluator, trade, depin, compute-grid…
HiveTrust — v1.0.0
KYA identity verification, trust scoring, and performance bonds for AI agents
io.github.Startvest-LLC/idealift-mcp — v1.0.0
Pre-backlog idea management with decision tracking, signals, and RICE scoring.
io.github.stillmarcus24/stillos-notary — v1.0.0
Signed, x402-paid StillOS notary tools: claim verdicts, OFAC screening, distress scoring.
io.github.sugar-co-dev/roc-mcp-server — v1.0.0
Creator commerce intelligence for TikTok Shop brands — benchmarks, ROC calculator, and brand fit.
Search1API — v0.5.3
Web search, news, page retrieval, sitemaps, and trending topics through Search1API.
io.github.supertrained/rhumb-mcp — v0.8.2
Agent gateway for Index discovery, AN Score evaluation, and Resolve governed execution
io.github.teflon07/memkeeper — v0.5.3
Local-first memory for AI agents: on-device hybrid retrieval over a single SQLite file.
io.github.TheNextGenNexus/hr-compensation-mcp-server — v1.0.1
Search H1B visa salaries, salary benchmarks, and job market data
qsearch — v0.4.0
Multi-engine search for AI agents. Trust scoring, local corpus, MCP-native. Self-hostable, BYOK.
agentmem — v0.2.5
Governed memory for coding agents. Trust lifecycle, conflict detection, health scoring.
Telys — on-device memory — v0.1.1
Private on-device memory & retrieval for AI assistants — offline vector + lexical search.
io.github.timolein74/asterpay — v1.0.2
EUR settlement for AI agents. Trust scoring, market data, crypto analytics. 16 free tools.
io.github.TinySuiteHQ/tinycontext — v0.2.1
Token-light local memory with SQLite hybrid retrieval for MCP agents.
io.github.tjacquesson/llmtest-mcp — v0.6.1
Benchmark AI models on real prompts. Find cheaper, faster alternatives across 340+ models.
Research Repo Doctor — v0.2.24
Deterministic Artifact Evaluation preflight and run-path grader for research repositories.
io.github.truecalc/truecalc-mcp — v7.1.1
MCP server exposing TrueCalc spreadsheet formula evaluation as tools for AI assistants.
io.github.turbyho/mem-context — v0.1.4
Temporal memory MCP server with LanceDB vector search, weight-decay scoring, and LLM consolidation
io.github.uchit/aipatterns-mcp-server — v1.1.0
Search AU enterprise AI patterns, benchmarks, incidents, and regulatory changes.
dep-scout — v0.2.0
Help AI agents find and evaluate mature packages across 6 ecosystems instead of reinventing them.
Medicare Enrollment and Revalidation Data — v1.3.3
Free CMS enrollment and revalidation evidence with pay-per-result automation and Roster Watch terms.
Vantio Gate — v0.1.0
Vantio Gate — Policy Latch dry-run evaluate for agents. No live enforce from MCP.
CISSP Study Group - CISSP Exam Prep & Practice Questions — v1.0.0
CISSP exam prep: 3,600+ practice questions, study stats, and readiness scoring
io.github.vdappdev2/data — v0.1.7
MCP server for Verus on-chain data retrieval, decryption, signing, and verification
io.github.vdineshk/dominion-observatory — v1.1.0
Runtime behavioral trust scoring for MCP servers. Check reliability before calling unknown tools.
web-retrieval-mcp — v0.1.2
MCP web search + tiered web fetch for AI agents (Exa, Firecrawl), SSRF-guarded, cross-platform.
io.github.venomseven/nslookup — v1.6.0
DNS lookups, health reports, SSL certs, security scans, GEO scoring, uptime checks
Veri Asia — v1.0.0
Calibrated probabilities, fair odds and value plays for Asian football, benchmarked vs Pinnacle.
VerifyAX — v0.3.2
Evaluate, benchmark, and simulate AI agents on the VerifyAX agent-evaluation platform.
AuctionTrace — v1.0.0
Historical ES Book Pressure data, matched evidence, and evaluation guidance for $5 USDC via x402.
Bench Agent Discovery — v0.1.0
Discover public AI agents, reusable recipes, and trusted benchmark evidence by task.
AgentTrust — v0.1.0
Quality verification for AI agents and MCP servers. 6-axis scoring, adversarial probes.
io.github.VladUZH/sidclaw-governance-mcp — v0.1.13
Governance proxy for MCP servers — policy evaluation, human approval, audit trails.
io.github.voidfeedai-ops/voidfeed-mcp — v1.0.0
Knowledge API for AI agents — content, agent directory, model benchmarks, semantic search.
Vouch — v1.2.2
Git-native, review-gated knowledge base for LLM agents. Cited retrieval, audited writes.
io.github.vpatser1/seo-audit-tool — v1.1.4
SEO page audits with 0-100 scoring, keyword analysis, link checking, sitemap validation
io.github.vpatser1/social-media-analytics — v1.1.4
Profile analysis, hashtag research, content calendars, competitor benchmarks, viral scoring
io.github.wchiway/contextweaver — v1.5.4
Semantic code retrieval engine with hybrid search, context expansion, and 40+ language support.
AI Applyd — v1.2.0
ATS resume scoring, job analysis, interview prep, and auto-apply that verifies each submission.
Liveability MCP — v1.4.0
Liveability scoring for Japanese addresses: shopping, medical, transit, education, nature, safety.
io.github.wisdomrock/code-context-gate — v0.1.1
Context-aware code retrieval MCP server — ranked, gated results for AI coding agents
MindCore Memory MCP — v0.1.11
AI long-term memory MCP server with importance scoring and confidence calibration
agent-exporter MCP bridge — v0.1.2
Local stdio MCP bridge for archive publishing, retrieval, and governance evidence.
io.github.yakuphanycl/instinct — v1.0.0
Self-learning memory for AI coding agents with pattern detection and confidence scoring.
Learning Model Context Protocol — v0.2.0
MCP server that can perform basic arithmetic operations and parse/evaluate arithmetic expressions.
io.github.yashdoke7/skeletongraph — v0.1.1
Zero-LLM structural code retrieval for AI coding agents, served over MCP.
io.mcpskills/server — v2.5.3
Trust scoring for MCP servers, AI skills & npm packages — 15 signals + safety scanning.
MoltJobs — v0.2.0
Browse MoltJobs jobs, manage owned AI agents, review evals, and place authorized USDC bids.

Page 6 of 7

How this page is ordered

Entries are grouped by whether anyone is still working on them, using the date of the most recent push to the repository. They are not ordered by stars, because a star is a bookmark somebody left once and never took back.

Where we have not checked an entry yet, it says so rather than being mixed in with the verified ones.