MCP Servers

Long-term memory for AI agents (Claude Code/Desktop, Cursor, ChatGPT, Codex, OpenClaw) backed by a local Obsidian markdown vault. Hybrid retrieval (BM25 + ML embeddings + BGE reranker, RRF-fused), HNSW + int8 quantization, agentic RAG (HyDE + sub-question), GraphRAG-light (Louvain wikilink community detection), standalone Obsidian Bases, PDFs + Tesseract OCR. 46 tools, 19 MCP prompts, MIT, SLSA L2, zero cloud calls during serve. npx -y @oomkapwn/enquire-mcp serve --vault

Vault-native, accountable memory for Claude Code and any MCP client. Markdown is the source of truth, no LLM on the Stop path, redaction before every derived store.

Zero-config session continuity for Claude Code, OpenAI Codex CLI & Google Gemini CLI, sharing one local db. Auto context injection on start, compaction handover, and 24 tools for memory, tasks, solutions, and a knowledge graph. Multilingual semantic search (94+ languages), 100% local, $0 API cost. npm i -g passbaton

Local-first semantic memory server with hybrid search, plain Markdown storage, MLX or CPU embeddings, contradiction detection, time-travel history, synthesis, and cross-machine git sync.

Local-first persistent memory for AI agents. SQLite + local embeddings (all-MiniLM-L6-v2), hybrid semantic + FTS5 recall, secret detection, and contradiction handling. 6 MCP tools (remember, recall, forget, feedback, context, status) over stdio. Zero cloud, no API keys, fully offline. Works with Claude Desktop/Code, Cursor, and Windsurf. npm install -g @hbarefoot/engram

Graph-structured session memory for LLMs. Local OpenAI-compatible proxy that extracts tasks, decisions, and files into a typed knowledge graph, auto-checkpoints before context overflow, and resumes any session in ~250 tokens. 6 MCP tools including whydecision (traces why a decision changed, with reasons and evidence). pip install tokenmizer

Local-first long-term memory for terminal AI agents (Claude Code et al.) via Anchored Compacting. Stores blueprints, code anchors (file→line→concept), and distilled lessons in a single JSON under .zipmem/, restoring full cross-session project context at near-zero token cost. No DB, no API keys, no embeddings. npx zipmem-mcp

Codebase memory for coding agents, with no embeddings and no API key. A deterministic AST index answers "which files are relevant to this task?" in milliseconds, and agents write durable notes about the repo that are content-hash checked — a note flags itself stale the moment the code it describes changes. Notes are markdown inside the repo, so they commit and review alongside your code. npm i -g @cstart/coldstart && coldstart init

ISO 20022 bank-statement parsing + reversing entries (camt.053 Bank-to-Customer Statement). 19 tools + 3 resources + 4 guided prompts across message-type discovery, return-reason lookup, schema introspection, IBAN/BIC/LEI validation, camt.053 parsing + XSD validation, Nov 2026 CBPR+ cliff readiness check, curated SEPA / CBPR+ / HVPS+ rulebook citation lookup, accounting-platform journal export (Xero + QuickBooks Online), LLM-driven entry classification via MCP Sampling, entry listing/filtering,

🎖️ - Pay-per-call AI + web + on-chain tools for agents over x402 (USDC on Base) — no accounts, no API keys; the wallet is the identity. 11 tools incl. token rug/honeypot safety (0–100 score, risk band, buy/sell simulation), new-pairs / liquidity-pull / whale-swap signals, SEO/GEO audit, web extract, link preview, robots & security-headers checks, and LLM inference. Tools auto-discover from the live catalog. npx -y @true402.dev/mcp-server

Offline LLM cost prediction: estimate/predict request cost, select the cheapest capable model, compare models, list pricing, and optimize requests. 7 tools, no API keys, runs via npx @workswarm/modelcostsaver.

Live LLM API pricing from modelpricewatch.com — current token prices, model comparisons, cheapest-model lookups, and The LLM Price Index across 150+ models from 20+ providers, re-verified daily against official provider pages. No API key required. npx -y @modelpricewatch/mcp

Agent-payable APIs settled on Kaspa L1: text tools (summarize, schema-guaranteed extract, classify, rewrite), web reading, embeddings + semantic search, live Kaspa chain data, GPU LLM tiers, covenants-as-a-service, and RISC Zero zk proving with cycle-exact quotes. Pay per call in KAS, BTC, LTC, DOGE, BCH, DASH, ETH, or USDC — fractions of a cent, no account or API key. pip install k402-mcp

Lightning-paid (L402) Bitcoin mempool intelligence + sovereign on-prem AI inference. 25 pay-per-call tools: live fees with trend, whale/mempool alerts, fee prediction, tx status & exact fee quotes, plus AI summarize/translate/grammar/code-review/code-gen/extract/classify/rewrite/explain/vision/OCR/embeddings and long-context docs — all on a self-hosted solar-powered GPU, no third-party APIs, pay 2–100 sats per call. npm i -g @bitcoinbenji/mcp

MCP bridge for Distill — AI file renamer that analyzes content (PDF/OCR/Office/email/media) and renames files with descriptive names. Five AI providers (Claude, OpenAI, Gemini, Ollama, Apple Intelligence), pay-per-use credits, folder monitoring, 9 MCP tools.

Profiles tabular data files (CSV, TSV, Parquet, Excel, JSON) for LLM agents: one-call dataset overview, per-column statistics, a data-quality audit (missing values, duplicates, mixed types, outliers), and memory-saving dtype suggestions. Pure Python (pandas); files are read locally and nothing leaves your machine. pip install data-profiler-mcp.

Airtight math for agents: 3.7M-theorem search, PSLQ constant ID, OEIS, real Lean kernel checks, applicability checklists. No LLM inside, no API key.

Deterministic guardrail for AI-written diffs, runnable from inside the coding agent's own loop over MCP. Zero-LLM-token, AST-precise rules (SQLi, SSRF, XXE, permissive CORS, prototype pollution, hardcoded secrets) across 8 languages, plus structural checks for reinvented helpers and over-abstraction — findings scoped to only the changed lines, same input always gives the same output, no false-block guarantee. npm i -g diffgate-review (registers as the diffgate command; diffgate mcp starts the se

MCP server for quelllm.fr — open-weights LLM catalog (250+ models with params, VRAM by quantization, tokens/sec, license). Tools: listmodels, getmodel, compare, estimatevram, estimatecost (API providers vs self-hosted hardware in EUR), searchmodels. Useful when picking a local model that fits your GPU/Mac.

🎖️ - Guardrail that checks agent-written code against a repo's own git-history-learned patterns — flags foreign dependencies, reinvented functions, misplaced code, broken layering, and gamed tests. Exposes voicecontext (the repo's familiar imports/idioms for a file, so agents write in-voice before generating), check (score a generated hunk against the repo's patterns), and explain. 100% local, no LLM, single Rust binary. npm i -g @tmonier/argot

Semantic codebase search + persistent working memory for AI code editors. Hybrid dense + BM25 search over AST-aware chunks, a symbol graph for locate/trace, and typed notes that survive context compaction and session restarts. Local embeddings, zero config, no API key. pip install vectr

Structural code context server for AI agents — compressed symbol indexes, dependency graphs, and git diffs via TypeScript AST analysis. Zero external dependencies, no vector database or embedding API required.

Offload cheap work from your cloud LLM agent to a local Ollama model — summaries, drafts, extractions, and first-pass code reviews via purpose-built handoff tools with baked-in prompts, at zero cloud cost.

Bug-report triage and fix-dispatch MCP for vibe coders. Ask your AI coding agent for a plain-English diagnosis of any user-reported bug — with evidence, blast radius, and a paste-ready fix prompt — then dispatch an automated GitHub fix PR without a second LLM key. 80+ tools, Supabase-backed, MIT SDK. npx @mushi-mushi/mcp