标签：#mcp

Hermes AI Agent handles multi-step workflows well. The planning layer holds up. Memory across sessions works. What kept breaking down was the tool layer. Once a workflow touched three or four external systems, I was spending more time on auth configs, mismatched response formats, and per-tool retry logic than on the workflows themselves. I fixed this by routing all external tool calls through a unified MCP gateway. The agent logic stayed the same. The integration complexity moved into one place I could actually manage. This post walks through how that works, how to set it up, and where it is genuinely useful. How Hermes runs tasks Hermes is an open-source, self-hosted agent runtime from Nous Research, released in February 2026 under the MIT license. It runs persistently on your own infrastructure and executes goals as structured, stateful workflows. Four layers handle execution. The planning layer breaks a goal into sequenced steps and adjusts them as intermediate results come in The execution layer runs each step and fires tool calls when external data or action is needed The memory layer stores task state and session history in SQLite with FTS5, so context carries over across restarts The skills layer captures completed workflows as reusable documents retrieved on future tasks After a task finishes, Hermes writes a skill file with the procedure and known failure points, then stores it for retrieval next time a similar task runs. Tool execution is embedded in the runtime loop. External capabilities come through MCP-based interfaces, which is where the gateway plugs in. What breaks when integrations live inside the agent In a standard MCP setup, each client connects one-to-one with a specific MCP server. That works fine with two or three tools. With ten, it becomes a maintenance problem that grows with every tool you add. A task spanning a web search, a product API, and a SERP scraper means three separate auth setups, three response formats to parse, and three diffe

Most explanations of atomic swaps stop at the spot case: two parties lock funds, one reveals a secret, both legs clear in the same short window. Clean, but it quietly assumes the trade settles right now . A lot of real agent activity isn't spot. It's a forward: two agents agree on terms today - asset pair, size, price - and settle at some future point, T+24h or T+48h. Procurement agents pre-committing to a delivery. A treasury agent locking tomorrow's FX-equivalent rate. A market-making agent quoting a forward to offload inventory risk. The economics are old; what's new is that the counterparties are anonymous software that will never meet. That raises a question spot swaps don't have to answer: what holds the trade together in the gap between agreement and settlement? In traditional markets the answer is a chain of intermediaries - a clearing house, posted margin, a credit desk that decides whether your counterparty is good for it. Strip those away, as you must in a market of anonymous agents, and the naive version of a forward collapses. If nothing binds the trade, either side can simply not show up when the price has moved against them. That's counterparty risk, and it's exactly the thing a forward is supposed to manage. This post is about how the HTLC primitive - the same hashlock plus timelock most people only associate with same-block atomic swaps - can encode a forward obligation that's binding without anyone custodying the funds in between. The timelock is doing more work than you think Recall the two parameters of a hash-time-lock contract: Hashlock: funds can only be claimed by revealing a preimage s such that hash(s) == H . The same H is used on both legs, so the act of claiming one leg reveals the secret that unlocks the other. That's what makes the swap atomic - both clear or neither does. Timelock: if the preimage isn't revealed before a deadline, the funds refund to their original owner. No third party decides this; the contract enforces it. In the sp

Giving an LLM a database connection is one of those ideas that sounds great in a demo and terrifying in production. The agent writes a slightly-wrong query, and now you're explaining to your team why orders is empty. So when I wanted an AI agent (Claude Desktop, in my case) to answer questions about a SQLite database, I didn't want to hand it a read-write connection and hope for the best. I built a small MCP server that gives the agent read-only SQL access — and I made "read-only" mean it, with two independent layers of protection. Here's how it works, and the design decisions that matter. Full source: github.com/skycandykey1/mcp-sqlite-server (MIT). A 30-second primer on MCP The Model Context Protocol (MCP) is an open standard for connecting AI apps to tools and data. An MCP client (Claude Desktop, Claude Code, Cursor, ...) connects to MCP servers that expose three kinds of capability: Tools — functions the model can call ( query , list_tables , ...) Resources — read-only data the model can pull in (a schema, a file) Prompts — reusable prompt templates The Python SDK ships a high-level helper, FastMCP , that turns this into a few decorators. The interesting part isn't the protocol — it's the safety design behind the tools. Design: keep the dangerous part away from the protocol The first decision: the read-only safety logic has zero MCP dependency. It lives in a plain module ( db.py ) that knows nothing about MCP, so I can unit-test it with nothing but the standard library. The server ( server.py ) is a thin wrapper. That separation matters: the part that must never be wrong (write protection) is testable in isolation, without spinning up an MCP client. Two layers of write protection A single guard is a single point of failure. So write protection happens twice, independently. Layer 1 — open the database read-only at the engine level: import sqlite3 def connect ( path : str ) -> sqlite3 . Connection : """ Open a SQLite database in READ-ONLY mode. Any write raises Op

Title: The agent economy added two rails and lost most of its volume this week. Nobody added settlement. Tags: mcp, ai, cryptocurrency, blockchain This is our weekly recap from building Hashlock in public. We try to read every agent-economy announcement of the week and ask one question of each: at the moment a trade actually clears, which layer finishes it? This week the answers lined up unusually neatly. The headline number: x402 is down 92% OKX Ventures published agent-payment data in June showing that x402 transaction volume has fallen roughly 92% from its November 2025 peak - from about $5.15M to $1.19M per month. Transaction count recovered (around 2.89M monthly), but the average transaction is now about $0.52. That is a category settling into micropayments, not a category absorbing real trade value. That is worth sitting with, because for most of the last year the narrative ran the other way: payment rails for agents were the story, and settlement was treated as a solved sub-problem of payment. The first hard volume number says the opposite. The rails are cooling. And yet the rails keep launching The same week, two more shipped: Mastercard Agent Pay - a way for agents to initiate card payments on a user's behalf. A Ripple XRPL agent kit - tooling for agents to move value over the XRP Ledger. Both are real, both are useful, and both do the same fundamental job: route a known asset from an agent to a seller. That is payment . It is also the layer that already has the most entrants, the most capital, and - per the x402 data - the softest demand relative to the hype. There is nothing wrong with a crowded payment layer. The point is narrower: launching more payment rails does not address the thing that is structurally missing. The map with a hole in it The most useful artifact of the week was OKX Ventures' framework for the agent economy. It describes three converging layers: Payment - x402 and similar (move value from agent to seller). Trust - ERC-8004 and agent r

HashiCorp has announced the general availability of the Terraform MCP Server, an open-source MCP server that enables agents to integrate with Terraform Registry APIs. The company says that it can improve infrastructure teams productivity by relieving engineers of rote tasks. By Sergio De Simone

Model Context Protocol (MCP): Giao Thức Kết Nối Thế Giới Cho Trí Tuệ Nhân Tạo Trong thế giới AI đang phát triển với tốc độ chóng mặt, việc xây dựng các ứng dụng thông minh, có khả năng tương tác linh hoạt với dữ liệu và công cụ bên ngoài là một thách thức lớn. Các mô hình ngôn ngữ lớn (LLM) như GPT, Claude, hay Gemini dù mạnh mẽ nhưng thường hoạt động trong "vùng cô lập", thiếu khả năng truy cập trực tiếp vào các hệ thống bên ngoài theo thời gian thực. Đây chính là lúc Model Context Protocol (MCP) xuất hiện như một giải pháp cách mạng. MCP là một giao thức mở, được thiết kế để tiêu chuẩn hóa cách thức các ứng dụng cung cấp ngữ cảnh (context) cho LLM, giúp phá vỡ rào cản giữa trí tuệ nhân tạo và thế giới thực. Bài viết này sẽ đi sâu vào phân tích Model Context Protocol , từ định nghĩa, kiến trúc, đến các lợi ích và ứng dụng thực tế, giúp bạn hiểu tại sao nó được coi là "ngôn ngữ chung" của tương lai AI. Model Context Protocol (MCP) Là Gì? Model Context Protocol (MCP) là một giao thức mở, được phát triển để tạo ra một chuẩn giao tiếp thống nhất giữa các LLM và các nguồn dữ liệu, công cụ bên ngoài. Hãy tưởng tượng MCP như một "cổng USB" dành cho AI. Thay vì mỗi ứng dụng AI phải viết mã tích hợp riêng lẻ với từng loại cơ sở dữ liệu, API, hay hệ thống tệp tin (mỗi loại một kiểu "phích cắm" khác nhau), MCP cung cấp một giao diện chuẩn. Bất kỳ ứng dụng nào hỗ trợ MCP đều có thể kết nối với bất kỳ nguồn tài nguyên nào cũng hỗ trợ MCP một cách liền mạch. Mục Đích Cốt Lõi Của MCP Mục tiêu chính của Model Context Protocol là giải quyết vấn đề "fragmentation" (phân mảnh) trong hệ sinh thái AI. Trước MCP, việc tích hợp thường diễn ra rời rạc: Mỗi nhà phát triển ứng dụng phải tự xây dựng các "kết nối" tùy chỉnh. Mỗi lần cập nhật mô hình hoặc công cụ có thể làm hỏng các tích hợp cũ. Khó khăn trong việc chia sẻ và tái sử dụng các công cụ AI giữa các dự án. MCP giải quyết những vấn đề này bằng cách cung cấp một lớp trừu tượng chuẩn hóa. Kiến Trúc Và Cách Thức Hoạt Động Của MCP Kiến

Hi HN, I built an open-source Java SDK for building Model Context Protocol servers: https://github.com/6000fish/mcp-java It is intended for Java developers who want to expose tools, resources, or prompts to MCP-compatible agents without implementing the protocol plumbing from scratch. The project includes: Core MCP server SDK stdio transport SSE transport Java API and annotation-based tool registration Spring Boot starter 5-minute quick-start example Copyable custom server template Ready-to-use MySQL and Redis MCP servers The SDK is available on Maven Central: <dependency> <groupId> io.github.6000fish </groupId> <artifactId> mcp-sdk </artifactId> <version> 0.1.1 </version> </dependency> <dependency> <groupId> io.github.6000fish </groupId> <artifactId> mcp-spring-boot-starter </artifactId> <version> 0.1.1 </version> </dependency> The MySQL and Redis servers are local stdio MCP servers, because database/cache connectors are usually safer to run inside the user's own environment instead of exposing credentials to a hosted remote endpoint. GitHub: https://github.com/6000fish/mcp-java Release: https://github.com/6000fish/mcp-java/releases/tag/v0.1.1 Feedback is welcome.

The AI landscape is shifting fast. Every week, a new agent framework, a new protocol, a new way for AI to interact with the world. But one thing has become painfully clear: most of our existing software was never built for AI agents to use. You have a SaaS product, a REST API, a database, maybe a frontend with useful actions. An AI agent cannot touch any of it without brittle browser automation or hand-written boilerplate. That is where MCPify comes in. MCPify is an open-source AI enablement compiler that transforms existing applications into AI-native, agent-operable systems. Instead of manually writing MCP server code for every tool you want an agent to use, you point MCPify at your codebase and it does the heavy lifting automatically. In this tutorial, I will walk you through turning any app into an MCP server using MCPify --- no prior MCP experience required. What Is MCP (Model Context Protocol)? Before we dive in, a quick refresher. The Model Context Protocol (MCP) is an open standard that defines how AI applications connect to external tools and data sources. Think of it as USB-C for AI agents --- a universal interface that lets any MCP-compatible client (Claude Desktop, Cursor, VS Code extensions, custom agents) talk to your services. An MCP server exposes tools that an AI agent can discover, inspect, and invoke at runtime. Building these servers manually for each endpoint, database query, or business workflow is tedious and does not scale. Enter MCPify: The MCP Server Generator MCPify ( https://github.com/amarnath3003/MCPify ) is an AI enablement compiler that scans your application and automatically generates a complete MCP server. It works by performing static analysis on your codebase --- frontend components, backend routes, API definitions, event handlers, and workflow logic --- and compiling that into MCP-compatible tools. Why MCPify stands out: Zero manual tool writing --- it discovers tools from your code automatically Permission-aware --- generated t

A useful thing happened in agent infrastructure this June: several teams shipped "escrow layers for AI agents" - production MCP tools that let an agent run a full commit -> hold -> complete lifecycle without a human anywhere in the loop. An agent can now park value with a contract or service, wait for the other side to deliver, and release on completion. That is genuinely new, and it solves a real problem. It is also worth being precise about, because "escrow" and "settlement" get used as if they were one thing. They are not. There are two structurally different ways to make a trade your agent does at 3am trustworthy, and the difference is exactly who holds the money while the trade is in flight . Model one: held custody In the held-custody model, a third party - a smart contract escrow, a custody service, a payment facilitator - takes the funds, holds them, and releases them when a condition is met. The condition can be anything you can express: a delivery confirmation, an evaluator's attestation, a timeout, a multi-sig approval. This is the right tool for a large class of agent commerce. If your agent is paying a merchant, buying a dataset, or hiring another agent to do a unit of work, the hard question is subjective : did the thing actually get delivered, and was it any good? A hash function cannot see that. A custodian can - it gives the trade a place to pause while something or someone checks. The new agent-escrow tooling is built around exactly this shape: a job, a held balance, a release on completion. For agent-to-merchant payments riding on rails like x402, held custody is the honest primitive. The cost is equally concrete. A held balance is a honeypot. Someone controls the funds between commit and complete, which means someone can freeze them, lose them, misconfigure the release condition, or get drained. You have added a trust assumption and a liveness dependency - the custodian has to be online, solvent, and honest at release time. That is often an accep

I ran the same browser smoke task through two paths: direct Chrome DevTools MCP and a custom CLI skill around mcp2cli . In GitHub Copilot CLI with gpt-5.3-codex-medium , direct Chrome DevTools MCP added about 5k tokens of upfront context before the agent did any work. The runtime table is too small and too noisy to rank the tools. The useful question is where the agent pays to discover the browser-control surface. mcp2cli README says it can “Save 96-99% of the tokens wasted on tool schemas every turn.” That is a strong claim and frankly I didn't no expect that sort of numbers... It's just the CLI part resonates with me - (a) there's no system prompt pollution with CLI, (b) if you choose between gh CLI and GitHub MCP the former would be better due to the fact that model already knows the tool and there's less tokens wasted on JSON schemas and tool calls. I used Chrome DevTools MCP a lot and I have chosen this MCP as a test bed to try mcp2cli . This came handy cause I started my experiments with the minimal pi coding agent and it doesn't bundle any MCP integration, just the basic bash tool, I was very much happy not to bloat my instal with a dedicated MCP plugin. Although in this cases I cmpared MCP vs CLI using a fully fledged GitHub CLI. Tool discovery is part of the experiment. Native MCP gives the agent a tool surface by loading schemas into context. A CLI wrapper makes the agent discover the surface the way it discovers any other command-line tool: list, search, ask for help, run a small probe, write down what worked. That changes where the discovery cost lands. The Setup I ran this in GitHub Copilot CLI using gpt-5.3-codex-medium : Copilot stock MCP servers were disabled. The app under test was a private Pythobn/Streamlit codebase. The browser task was the same 9-step smoke test in both variants. One variant used direct Chrome DevTools MCP. Another variant used a custom skill that wraps Chrome DevTools MCP via mcp2cli . The custom skill itself started as an ad-h

OAuth for Remote MCP Servers How each AI assistant signs in to a remote MCP (Model Context Protocol) server, and why the flow differs by client and by where it runs. Overview The protocol throughout is standard OAuth 2.1 — an open, widely implemented authorization standard. The human sign-in runs through oauth2-proxy , one of the most widely deployed open-source auth proxies; the only deployment-specific piece is a thin, spec-conforming authorization server (the /oauth endpoints) that hands MCP clients their tokens. Every client ends up the same way — a person signs in against Google (restricted to your organization's domain), and the client holds a short-lived bearer token it presents on each /mcp call. Two things differ between assistants: where the client runs (a machine on the VPN — private — vs. the vendor's cloud — public ), which decides the host it reaches; and what kind of OAuth client it is — a public client proving itself with PKCE (Proof Key for Code Exchange, which lets a client with no secret prove the token request comes from the same client that started the flow), or a confidential client proving itself with a secret. The participants oauth2-proxy — the public-facing reverse proxy. It authenticates the human against Google (the sign-in restricted to your organization's domain) and forwards the verified identity to the app behind it. Only oauth2-proxy faces the internet. It is a mature, heavily-deployed open-source project — the standard way to put Google/OIDC (OpenID Connect) single sign-on in front of a service, widely used in Kubernetes deployments — so the most security-sensitive leg of the flow (the OAuth exchange with the identity provider) runs on battle-tested code. The MCP server — the app on a loopback port behind the proxy. It plays two roles: the OAuth authorization server ( /oauth/authorize , /oauth/token , /oauth/register , .well-known discovery) and the /mcp tool endpoint. It mints codes and tokens, and validates a token on every /mcp c

If you've been following the AI-assisted development space, you've heard about the Model Context Protocol (MCP). But let's be honest—most MCP server lists are either too abstract or filled with niche tools you'll never use. In 2026, the ecosystem has matured, and I've curated 10 MCP servers that deliver real, measurable improvements to your daily coding workflow. Each entry includes: What it does Why it's useful (with a concrete scenario) Example config (using the standard .mcp.json or claude_desktop_config.json ) Let's dive in. 1. GitHub MCP Server (by modelcontextprotocol) What it does: Full read/write access to GitHub repos—issues, PRs, code reviews, and releases. Why useful: Instead of switching between your IDE and GitHub, your AI assistant can create a PR, request a review, and merge after CI passes—all from a single prompt. Example config: { "mcpServers" : { "github" : { "command" : "npx" , "args" : [ "-y" , "@modelcontextprotocol/server-github" ], "env" : { "GITHUB_TOKEN" : "ghp_xxxxxxxxxxxxxxxxxxxx" } } } } Scenario: "Create a new branch, add a fix for issue #42, push, and open a draft PR with a description." 2. Filesystem MCP Server What it does: Read, write, search, and manipulate files and directories on your local machine. Why useful: Your AI can now scaffold an entire project structure, rename files in bulk, or refactor code across multiple files without manual intervention. Example config: { "mcpServers" : { "filesystem" : { "command" : "npx" , "args" : [ "-y" , "@modelcontextprotocol/server-filesystem" ], "env" : { "ALLOWED_DIRS" : "/home/user/projects" } } } } Scenario: "Create a Next.js project with this folder structure, add a components folder, and move all page files into a pages directory." 3. PostgreSQL MCP Server What it does: Connect to PostgreSQL databases, run queries, and return results. Why useful: Debugging SQL queries or exploring a production database becomes a conversation. You can ask "Show me the last 10 orders with user details" a

Note: This is an English digest of the original Zenn post (Japanese) . Read there for the full timeline and commit-level trace. TL;DR We ship tasteck , a B2B SaaS for the Japanese night-leisure industry (dispatch + cast shift management). 8 years of operational data, ~100 venues live. Two days after the MCP design post , ChatGPT Plus can call our tools live: "Who's available tonight?" → MCP list_available_drivers → JSON → natural-language reply. Estimated B2 OAuth sprint = 2 weeks (6/16–7/1). Actual = 1 day , by reading the spec carefully before touching code. We hit 12 distinct traps between "OAuth issuance works" and "ChatGPT actually invokes the tool." The QA logs caught every one. What we shipped 3 read tools (B1): list_available_drivers — drivers free tonight list_cast_shifts — today's cast shift roster list_assignable_casts — joined resolution: roster ∧ stage-name set ∧ shop match Natural-language date helper: resolveBusinessDate(naturalText, company) — handles "today / tomorrow / day-after-tomorrow" and the per-tenant business-day boundary (e.g. day flips at 04:00 or 05:00, configured per Company.changeDateTime ). MCP SDK Server + SSE transport: @modelcontextprotocol/sdk wired into a NestJS controller. One SSE connection = one McpServer instance, company-scoped, with a session_id Map routing POST /messages . OAuth flow (B2, finished in one day across 7 steps) Step What Commit 1 Protected Resource Metadata endpoint (RFC 9728) d6f05ff6 2 /authorize + consent screen + PKCE start 107edbcb 3 /token + PKCE verify + JWT issue + resource (RFC 8707) ffd0468c 4 OAuthAccessTokenGuard (RS256 + HS256 fallback, extracts companyId / staffId ) f2c9bed4 5 Streamable HTTP transport (SSE → POST /sse/:companyId for JSON-RPC) 3a28d92f 6 resolveBusinessDate undefined fallback (`(naturalText 7 QA redeploy + ChatGPT live demo — The 12 traps (compressed) The full timeline is in the Japanese post; the abridged list: Discovery path mismatch. ChatGPT expected {% raw %} .well-known/oauth

The Model Context Protocol is everywhere right now. Every agent tutorial opens with "first, set up your MCP servers." And yet the agent stack running on the machine I'm typing this from — search monitoring, Telegram alerting, social posting, a voice assistant — contains exactly zero MCP servers. Everything talks to external services through direct API calls. That's not a rejection of MCP. It's a protocol, not a movement — and the flood of agent-architecture content keeps turning plumbing decisions into identity decisions. You're not an "MCP shop" or "behind." You're making a per-workload integration choice, and it comes down to two gates: one decides whether MCP is even the relevant category, the other decides whether it's worth the overhead. Gate one — relevance: does a model pick the tool at runtime? MCP exists to solve a specific problem: a language model, mid-session, deciding which tool to use. The protocol standardises how a model discovers tools, what their schemas look like, and how results come back. That's its entire reason to exist — it's a model-facing protocol. If no model is ever choosing, MCP isn't the relevant category; you'd share a library or stand up a plain service. Now look at what most automation actually is. My morning report pipeline: Cron fires at 8:30 Script calls the Google Search Console API Script formats the numbers Script posts to Telegram The model isn't deciding anything here. There's no runtime tool choice — the model's only job in pipelines like this is reading the data at one step, not fetching it. The call order is fixed, every day, forever. For this workload, MCP isn't the question. One subtlety that matters later: gate one is evaluated over a tool surface's consumers , not over the workload in front of you. The cron pipeline will never pass it. But the search-data access underneath it might — the day a model-driven client wants the same data. The pipeline isn't an MCP candidate; the surface can become one. Either way: being an

Your MCP server works. But does anyone know it exists? We scored 39,762 MCP servers. 54% scored Grade C — solid code quality, zero community adoption. They're invisible to the AI agents that need them. Here's how to go from invisible to discovered. What Your Grade Actually Means Our scoring uses an additive model: Composite Grade = Quality Score (0-100) + Community Bonus (0-60) + Trust Bonus (0-30) Grade Score What it means B+ 86+ Very good — close to elite B 76-85 Good — your target C+ 66-75 OK — getting there C 46-65 Average — this is 54% of all tools D 21-45 Needs work F 0-20 Critical If you're at C, you're not failing. You just haven't been discovered yet. Step 1: Fix Your Quality Score (Quick Wins) Quality Score is 5 dimensions. Here are the fastest fixes: Token Efficiency (25%) Every token in your tool definition counts against the agent's context window. Bad: 500+ tokens OK: 200-350 tokens Good: 100-200 tokens Elite: ≤50 tokens Fix: Cut redundant parameters. Shorten descriptions. Use concise naming. Most tools can save 40-80 tokens in 15 minutes. Schema Correctness (25%) Agents need machine-readable schemas. Fix: Add a type field. Define properties . Include required fields. A well-structured schema can add 30+ points to your quality score instantly. Description Quality (20%) Write for AI agents AND humans. AI agents need clarity. Humans need to understand what your tool does at a glance. A good description serves both. ❌ Bad (confuses everyone): "PDF tool" ✅ Good (clear to both agents and humans): "Extracts text and tables from PDF files. Supports multi-page documents. Returns structured JSON with page numbers." ✅ Better (humans can instantly understand, agents can parse): "Extracts text and tables from PDF files. Example: extract_tables('report.pdf') → [{page: 1, rows: [[...]]}]. Supports multi-page documents." A human scanning GitHub repos decides in 3 seconds whether to try your tool. An AI agent scanning tool definitions decides in 3 milliseconds. Serve

AI coding agents are useful, but they still have one frustrating habit: They guess. You ask something reasonable like: “Where do we validate user input before inserting into the database?” And instead of knowing where to look, the agent starts reading files one by one. In a small project, that is fine. In a real production codebase with 80,000+ lines, multiple engineers, old decisions, half-renamed folders, and years of accumulated context, this gets messy fast. The agent reads a handful of files, hits context limits, and gives you an answer that sounds confident but points to the wrong part of the codebase. I got tired of that, so I built an open-source MCP toolkit to fix it. What I Built I built MCP Server Toolkit , a collection of four Model Context Protocol servers that give AI coding agents direct access to the things they need: Your codebase Your database Your docs Your git history Repo: https://github.com/naveenayalla1-CS50/mcp-server-toolkit The goal is simple: Stop making the agent guess. Give it tools that know where to look. Why MCP? The Model Context Protocol, or MCP, lets AI agents call external tools in a standardized way. Instead of the agent reading random files and hoping the right context fits, it can call a purpose-built tool like: search_code("validate user input") And get back file paths, line numbers, and relevant context. That means fewer wrong guesses, fewer wasted tokens, and much better answers in large codebases. The Four Servers 1. mcp-code-search Searches across your repo and returns relevant matches with file paths, line numbers, and surrounding context. Example: You: Find all places where we call sendEmail Agent calls search_code("sendEmail") Results: api/users.ts:89 services/email.ts:42 jobs/reminders.ts:117 It also includes targeted read_file and list_files tools so the agent can inspect only the files it actually needs. 2. mcp-database Lets the agent ask read-only database questions in natural language. Example: You: How many users

Been doing a lot of competitive research for clients lately — checking hashtag volumes, tracking top posts in a niche, that kind of thing. Kept switching between Claude Code and browser tabs to cross-reference stuff manually. Got annoying fast. Found hikerapi-mcp, a Model Context Protocol server that exposes 100+ Instagram endpoints as tools directly inside Claude Code. Figured I'd try it. Setup was straightforward. The one thing I did differently was keeping the API key out of config files entirely — passed it as an environment variable instead. Smaller attack surface if I accidentally commit something. Also filtered down the tool groups with HIKERAPI_TAGS because 100+ tools showing up in context is chaos. I only need hashtag search and competitor profile data, so I scoped it to just those. "env": { "HIKERAPI_KEY": "${HIKERAPI_KEY}", "HIKERAPI_TAGS": "User Profile,Post Details,Search,Hashtags,Stories" } One thing that tripped me up for a solid 20 minutes: HikerAPI runs on a prepaid model (credits in rubles). If your balance is zero, you get HTTP 402, not 401. I kept thinking my key was invalid and regenerated it twice before I figured out I just needed to top up. Once that was sorted, it actually works well. Now I can ask things like "what are the top 10 posts for #socialmediamarketing this week" or pull a competitor's recent content directly in the same session where I'm building the campaign strategy. Cuts out a lot of context switching. Repo if you want to check it out: github.com/subzeroid/hikerapi-mcp Wrote up the full setup with config details here if useful: https://dev.to/simrp360/querying-instagram-from-claude-code-wiring-up-hikerapis-mcp-server-57jf Anyone else using MCP servers for social data research? Curious what other setups people are running.

Birgitta Böckeler, Distinguished Engineer at Thoughtworks, returns to discuss the rapid evolution of AI in software delivery. She touches on the evolution from vibe coding, the changing tools landscape and the more autonomous agents that, besides higher velocity, introduce higher risk. By Birgitta Böckeler

Key takeaways Give an AI agent live web data by connecting it to Crawlora's hosted MCP endpoint — it calls documented tools (search, maps, commerce, social, finance) and gets normalized JSON back, with no scraping code or proxies to run. MCP (Model Context Protocol) is an open standard: agents discover and call tools through one interface instead of a bespoke integration per data source. Connect over Streamable HTTP at https://mcp.crawlora.net/mcp with your API key — about three minutes in Claude, Cursor, Cline, Windsurf, or any MCP client. One connection exposes 319 tools across 33 platforms (393 REST endpoints underneath): Google/Bing/Brave search, Google Maps, Amazon, YouTube, TikTok, Yahoo Finance, CoinGecko, and more. You pay only on a successful (2xx) response — failed calls are free — and the free tier includes 2,000 credits a month with no card. Versus writing your own scrapers: no per-source glue code, normalized JSON instead of HTML, and proxy routing, rendering, and retries handled behind the endpoint. You can give an AI agent live web data by connecting it to a hosted MCP endpoint : your agent calls documented tools — search, maps, e-commerce, app stores, social, finance, and more — and gets back normalized JSON, with no scraping code to write or proxies to run. This guide explains what MCP is, what data you can pull, how to connect in about three minutes, and what a real tool call and its response look like. Most LLMs are frozen at their training cutoff and can't see the live web. The usual fix — writing a scraper per source, then maintaining proxies, headless browsers, and parsers — is exactly the work teams don't want to own. MCP plus a hosted data server removes it: the model gets a stable set of tools, and the fetching lives behind an endpoint. What is MCP, and why does it matter for agents? The Model Context Protocol (MCP) is an open standard that lets an AI agent call external tools through one consistent interface. Instead of wiring a bespoke int

Most "Bitcoin in DeFi" stories quietly route through a custodian or a wrapped representation. You send BTC somewhere, someone (or some bridge multisig) holds it, and you get an IOU on another chain. That works until the thing holding your BTC is the thing that fails. For an autonomous agent that has to post collateral against an obligation it can't babysit, "trust the custodian" is exactly the assumption we're trying to delete. This post is about the alternative: a BTC collateral vault where native Bitcoin backs an obligation on another chain, the release is gated by a hashlock, and the worst case is a refund — not a loss. It's one of the primitives underneath Hashlock's settlement layer. I'll walk through the timelock ordering that makes it safe, the Bitcoin script that enforces it, and the failure modes you design around. Honest status up front: this is signet-validated, not BTC mainnet . The problem in one sentence An agent wants to commit BTC as collateral backing an action on Ethereum — settling a forward, anchoring one leg of a multi-leg trade, guaranteeing a payout — such that the BTC is released to the counterparty only if the corresponding obligation on Ethereum is fulfilled, and returns to its owner if it isn't. No third party should ever be able to hold, freeze, or abscond with the BTC in between. That's a cross-chain conditional. Bitcoin can't read Ethereum state, and Ethereum can't read Bitcoin's. The only thing both chains can independently verify is a hash preimage. So the entire construction hangs on one shared secret. The shared secret, and why timelock order is the whole game Both legs lock to the same hash H = SHA256(s) . Whoever knows the preimage s can claim. The instant s is revealed on one chain to claim a coin, it's public, and the other party copies it to claim the other coin. That's the atomic part: one preimage unlocks both legs or neither. The danger isn't the hash. It's time . If both legs had the same expiry, the party who knows the sec