Home › Search: eval

Search: eval

Search MCP servers and agent skills by name, description, category or topic — 95 results.

MCP Server Active

renezander030/agentic-task-system

Turns your task manager into agent memory: hybrid (dense + sparse + keyword, RRF) retrieval over TickTick or an Obsidian vault via a six-method adapter contract. MCP server + CLI, no vector DB to build or maintain. `npm i -g @reneza/ats-cli`

9 JavaScript Updated 12d ago Score 60
MCP Server Active

huj28-creator/wechat-fastbridge

Token-efficient macOS WeChat MCP server for verified chat reading, text/file/sticker sending, fuzzy safe routing, smart context retrieval, and allowlisted live monitoring without screenshots or private-protocol access.

7 JavaScript Updated 10d ago Score 59
MCP Server Active

ayhammouda/python-docs-mcp-server

Local, read-only retrieval over official Python standard library docs with exact symbol lookup, section-level results, and version-aware context.

7 Python Updated 5d ago Score 59
MCP Server Active

OrygnsCode/opa-mcp-server

Open Policy Agent (OPA) and Rego policy toolkit. 32 tools spanning authoring (format, lint, check, deps), evaluation (eval, test, bench, coverage), and OPA REST control (policies, data, decisions, compile). Wraps the OPA CLI and the [Regal](https://github.com/StyraInc/regal) linter, with AI-assisted helpers for explaining decisions, generating test skeletons, and suggesting fixes.

7 TypeScript Updated today Score 59
MCP Server Active

QuantToGo/quanttogo-mcp

Macro-factor quantitative trading signals for AI agents. 8 tools for strategy discovery, live signal retrieval, and self-service trial registration. Covers US and A-Share markets with forward-tracked performance.

6 Python Updated 5d ago Score 58
MCP Server Active

billy12151/memory-arbiter-mcp

AI enhancement middleware: precise retrieval replaces full-memory loading (~80%+ token cut), rule-based conflict arbitration with explainable reasons, and one local SQLite shared across Claude Code/Codex/Cursor/ZCode. Local-first, zero cloud, MIT. `pip install memory-arbiter-mcp`

6 Python Updated today Score 58
MCP Server Active

udjin-labs/mnemostack

Durable hybrid memory for AI agents. Combines vector search, BM25, temporal retrieval, and optional Memgraph knowledge graph via reciprocal rank fusion. 6 MCP tools: health, search, answer, feedback, graph_query, graph_add_triple. Self-hosted with Qdrant backend. 82.5% strict accuracy on LoCoMo benchmark. `pip install 'mnemostack[mcp]'`

6 Python Updated 5d ago Score 58
MCP Server Active

vassiliylakhonin/agenda-intelligence-md

Auditable strategic-risk memos for AI agents — sanctions, regulatory, geopolitics, trade. Geography-routed regional specialists (Central Asia/Caspian, Gulf/Middle East), per-claim evidence discipline, schema-validated output, machine-verified audit. No live data retrieval. PyPI: `agenda-intelligence-md`.

6 Python Updated yesterday Score 58
MCP Server Official Active

everstake/mcp

An MCP server for Everstake's non-custodial staking data across 130+ networks: live APY, uptime metrics, rewards calculator, integrations, security and compliance. Built for asset managers, custodians, and exchanges evaluating institutional staking.

1 Go Updated 22d ago Score 58
MCP Server Maintained

Quantum3-Labs/ARBuilder

AI-powered code generator for the Arbitrum ecosystem. 19 MCP tools for Stylus smart contracts, SDK bridging, full-stack dApps, and Orbit chain deployment, backed by RAG-based retrieval over Arbitrum documentation.

24 TypeScript Updated 2mo ago Score 57
MCP Server Maintained

ByteAsk/ByteAsk-Embedded-MCP

Page-cited retrieval of embedded/firmware reference docs (datasheets, MCU registers, Modbus/CAN, SCPI, IEEE 1547/SunSpec) for coding agents — returns verbatim source snippets with page citations, or "no confident match" instead of a fabricated value. No signup or API key.

23 Python Updated 1mo ago Score 57
MCP Server Active

zlatkoc/youtube-summarize

MCP server that fetches YouTube video transcripts and optionally summarizes them. Supports multiple transcript formats (text, JSON, SRT, WebVTT), multi-language retrieval, and flexible YouTube URL parsing.

4 Python Updated 2d ago Score 57
MCP Server Official Stale

heurist-network/heurist-mesh-mcp-server

Access specialized web3 AI agents for blockchain analysis, smart contract security auditing, token metrics evaluation, and on-chain interactions through the Heurist Mesh network. Provides comprehensive tools for DeFi analysis, NFT valuation, and transaction monitoring across multiple blockchains

66 Python Updated 4mo ago Score 56
MCP Server Active

gvasile29/qai-consultant

Keyless local MCP server bringing ISTQB / OWASP / IEEE / ISO / EU AI Act QA standards into your AI client: standards-grounded retrieval, deterministic QA effort estimation, and automated QA document quality review (0-100 rubric) plus JUnit/CSV test-results flakiness analysis. `uvx qai-consultant-mcp`

3 Python Updated yesterday Score 56
MCP Server Active

carrasquelalex1/hipocampo

Dual-memory MCP system (PostgreSQL 17 + pgvector + NVIDIA NIM). 11 tools: search, save, profile, health, auto-repair, stats, tune, dedup, checkpoint, maintenance. Sparse Selective Caching (SSC) with 4-phase progressive retrieval. Bilingual EN/ES. `python scripts/hipocampo_mcp_server.py`

3 Python Updated 6d ago Score 56
MCP Server Active

cipherfoxie/sovereign-mcp

MCP for the [Sovereign AI Blog](https://sovgrid.org), a hands-on engineering log of self-hosted AI on NVIDIA DGX Spark (GB10/SM121A). 44+ articles covering SGLang, Mistral, Voxtral, OpenClaw. Three tools: full-text search, article retrieval, and SGLang config validator for GB10 hardware. Free, no auth, no client-side tracking. `https://mcp.sovgrid.org/self-hosted-ai?ref=awesome-mcp`

3 Python Updated 12d ago Score 56
MCP Server Stale

redleaves/context-keeper

LLM-driven context and memory management with wide-recall + precise-reranking RAG architecture. Features multi-dimensional retrieval (vector/timeline/knowledge graph), short/long-term memory, and complete MCP support (HTTP/WebSocket/SSE).

153 Go Updated 6mo ago Score 55
MCP Server Official Active

sendchamp/ai

Official Sendchamp docs MCP server for AI coding agents. Read-only search and retrieval over SMS, OTP verification, and Africa-specific routing documentation. Endpoint: `https://mcp.sendchamp.com/docs`. Pair with Agent Skills via `npx skills add sendchamp/ai`.

0 TypeScript Updated 16d ago Score 55
MCP Server Maintained

vectorize-io/vectorize-mcp-server

[Vectorize](https://vectorize.io) MCP server for advanced retrieval, Private Deep Research, Anything-to-Markdown file extraction and text chunking.

109 JavaScript Updated 1mo ago Score 53
MCP Server Maintained

lorenzo-cambiaghi/LynxMCP

100% local semantic code search for AI agents: AST-aware chunking (tree-sitter), hybrid BM25+dense retrieval, and a code knowledge graph (callers, inheritance, imports) over codebases, docs sites, and PDFs. Install via `pipx install lynx-mcp`.

8 Python Updated 1mo ago Score 53
MCP Server Active

verifyax/verifyax-mcp

MCP server for the VerifyAX platform. Enables agent evaluation, simulation testing, and functional/non-functional verification workflows through natural language.

1 TypeScript Updated 4d ago Score 53
MCP Server Active

laszlopere/mcp-abacus

Type-faithful calculator: evaluate expressions under fixed-point, IEEE-754 double, or exact rational arithmetic, with every answer labelled exact vs inexact. Tools: calculate, analyze, solver, help, info. Offline, no network. `uvx mcp-abacus`.

1 Python Updated 7d ago Score 53
MCP Server Active

0rkz/byte-mcp-server

PayPerByte — per-byte data marketplace for AI agents on Arbitrum. Discover publishers, evaluate on-chain Proof-of-Quality Score (PQS), subscribe + pay per request in USDC via x402 gateway. 15 tools, zero API keys.

1 JavaScript Updated 11d ago Score 53
MCP Server Active

AIDataNordic/Food-Recipe-MCP

Semantic search across 50,000+ Food.com recipes with hybrid dense+sparse retrieval and cross-encoder reranking. Filter by diet, cooking time and difficulty. Live remote endpoint available.

1 Python Updated 18d ago Score 53
MCP Server Maintained

krimto-labs/krimto

Open-source team memory layer for AI coding agents. Markdown files in git as storage, a user→team→org hierarchy as the access primitive, and one cross-vendor MCP server (Claude Code, Cursor, Codex, Gemini CLI). Hybrid SQLite + sqlite-vec retrieval. Apache-2.0.

6 TypeScript Updated 2mo ago Score 51
MCP Server Maintained

khalidsaidi/ragmap

MapRag: RAG-focused subregistry + MCP server to discover and route to retrieval-capable MCP servers using structured constraints and explainable ranking.

5 TypeScript Updated 2mo ago Score 51
MCP Server Official Stale

Perspective-AI/mcp

Official MCP server for [Perspective AI](https://getperspective.ai). An AI Concierge replaces static forms with adaptive AI conversations for lead qualification, customer research, onboarding feedback, and advocacy. Design conversation agents (Concierge, Interviewer, Evaluator, Advocate), analyze conversations, deploy embeds, and automate follow-ups (webhook, email, Slack, HubSpot).

5 Shell Updated 3mo ago Score 51
MCP Server Active

smythmyke/govtoolspro-mcp-server

Workflow tools for US federal contractors — go/no-go bid scoring, incumbent intelligence (USAspending + FPDS), teaming-partner search, recompete prediction, Navy NECO lookup, and SAM.gov solicitation retrieval. Returns synthesized decisions rather than raw data.

2 TypeScript Updated yesterday Score 50
MCP Server Active

shuji-bonji/xcomet-mcp-server

Translation quality evaluation using xCOMET models. Provides quality scoring (0-1), error detection with severity levels (minor/major/critical), and optimized batch processing with 25x speedup.

2 TypeScript Updated 6d ago Score 50
MCP Server Active

Alepha188838884/context-firewall

Local proxy that collapses N downstream MCP servers into 4 meta-tools with progressive tool discovery (measured: 122 tools → 4, ~28.6K tokens of definitions saved), compresses large tool outputs (HTML→Markdown, JSON structure summarization, base64 stripping — 60–95% measured on real pages/APIs) with full-output retrieval via `read_more`, and prints a per-session token-savings report. Security-rele

0 TypeScript Updated 4d ago Score 50
MCP Server Active

argosvix/mcp-server

Observability for AI agents: 87 tools to query LLM cost, errors, and latency across OpenAI/Anthropic/Gemini/Mistral, and operate alerts, budget gates, evals, and safety checks from Claude/Cursor. Install: `npx -y @argosvix/mcp-server`.

0 TypeScript Updated today Score 50
MCP Server Active

ankitkapur1992-hlido/hlido-mcp

Independent trust scores, claim audits, and comparisons for AI agents — queryable by your agent over MCP. Hosted Cloudflare Worker at hlido.eu/mcp (no install). Returns a 0–100 score, tier verdict, per-claim PASS/FAIL audit, and signed evidence for a reviewed agent. From [Hlido](https://hlido.eu).

0 JavaScript Updated 17d ago Score 50
MCP Server Maintained

mumez/pharo-smalltalk-interop-mcp-server

Pharo Smalltalk integration enabling code evaluation, class/method introspection, package management, test execution, and project installation for interactive development with Pharo images.

12 Python Updated 1mo ago Score 49
MCP Server Maintained

supertrained/rhumb

Agent-native tool intelligence across 1,000+ scored services. 21 MCP tools: discover services, check AN Scores, compare alternatives, resolve capabilities to ranked providers, execute through 3 credential modes (managed, BYOK, agent vault), track costs with receipts, and inspect failure modes. Zero-signup option via x402 micropayments.

3 Python Updated 1mo ago Score 49
MCP Server Active

soolaugust/0CompactMem

Persistent memory MCP server with OS-style demand paging, kswapd-style eviction, and mlock pinning. Multi-agent shared SQLite store with BM25 + FTS5 retrieval, importance scoring, and capacity-aware reclaim. 5 tools: `memory_lookup`, `pin_memory`, `unpin_memory`, `memory_stats`, `list_pinned`. `uvx --from git+https://github.com/soolaugust/0CompactMem memory-os`

4 Python Updated 19d ago Score 47
MCP Server Stale

tan-yong-sheng/ai-vision-mcp

Multimodal AI vision MCP server for image, video, and object detection analysis. Enables UI/UX evaluation, visual regression testing, and interface understanding using Google Gemini and Vertex AI.

69 TypeScript Updated 3mo ago Score 46
MCP Server Maintained

parasxos/cpp26-adapter

C++26 paper reference MCP (`cpp26-ref`) backing a Claude Code plugin: `lookup_paper`, fuzzy `search`, `compiler_status` over a 216-paper ISO/IEC 14882:2026 corpus. The plugin's skill + reviewer subagent use these tools to bias Claude toward reflection, contracts, `std::execution` senders, `#embed`, expansion statements — even when the local compiler lags. 95% on a held 39-task eval gate.

1 Python Updated 2mo ago Score 46
MCP Server Maintained

lihtness/gnomon-mcp

Deterministic batch tools so LLM agents stop next-token-guessing dates and math. Rich `now()` snapshot (18 fields), `calendar(ops)` batch dispatcher (diff/until/since/add/weekday/business_days, natural-language parsing), `calc(expressions)` Python eval with math+stats pre-loaded, and Pint-based unit conversion. One wiring for dates + math + units. Listed in the official MCP Server Registry. `uvx g

1 Python Updated 2mo ago Score 46
MCP Server Maintained

sh6drack/zen-mcp

Zen Browser automation via WebDriver BiDi. 20 tools for navigation, form filling, screenshots, and JavaScript evaluation. No Selenium or Playwright required.

15 JavaScript Updated 2mo ago Score 45
MCP Server Maintained

sF1nX/x402station

Preflight by [x402station.io](https://x402station.io) — infrastructure for x402 agentic commerce. Six capability directions (Discover/Evaluate/Pay/Monitor/Recover/Analyze). Agents call it before every `PAYMENT-SIGNATURE` to detect decoys, zombie endpoints, dead services, and price traps. Tools: `preflight` ($0.001), `forensics` ($0.001), `catalog_decoys` ($0.005), `alternatives` ($0.005), `whats_n

3 JavaScript Updated 2mo ago Score 44
MCP Server Stale

debridge-finance/debridge-mcp

Cross-chain swaps and bridging across EVM and Solana blockchains via the deBridge protocol. Enables AI agents to discover optimal routes, evaluate fees, and initiate non-custodial trades.

32 TypeScript Updated 4mo ago Score 43
MCP Server Stale

memstate-ai/memstate-mcp

Versioned, structured memory for AI agents. Stores facts as keypaths with full version history, automatic conflict detection, and O(1) token retrieval.

7 TypeScript Updated 4mo ago Score 42
MCP Server Maintained

KOVY/agentforge-trust-mcp

Query the AgentForge Trust Score (0-100 across five dimensions: security, code health, behavioral audit, community trust, EU compliance) for any MCP server before connecting. Exposes `check_trust`, `evaluate_policy`, `list_trusted`, and `recommend` tools. 3,600+ servers audited, free public API.

1 TypeScript Updated 2mo ago Score 41
MCP Server Stale

ShipItAndPray/mcp-turboquant

LLM quantization via tool call. Convert models to GGUF, GPTQ, and AWQ formats. Recommend optimal quant settings, evaluate quality, and push to Hugging Face Hub.

4 Python Updated 4mo ago Score 40
MCP Server Stale

mattjoyce/mcp-persona-sessions

Enable AI assistants to conduct structured, persona-driven sessions including interview preparation, personal reflection, and coaching conversations. Built-in timer management and performance evaluation tools.

12 Python Updated 5mo ago Score 39
MCP Server Stale

ARKALDA/hejdar-mcp

Runtime policy enforcement for AI agents. Evaluate actions against organization policies before execution, with observe and enforce modes.

1 Python Updated 3mo ago Score 31
MCP Server Inactive

kunallunia/twitter-mcp

All-in-one Twitter management solution providing timeline access, user tweet retrieval, hashtag monitoring, conversation analysis, direct messaging, sentiment analysis of a post, and complete post lifecycle control - all through a streamlined API.

60 Python Updated 1y ago Score 28
‹ Prev12