MCP Dev Summit Seoul 2026

MCP Dev Summit Seoul 2026

10:55 KST

Stateful AI Agents: Building Consistent Systems with MCP and Distributed SQL - Nasiullha Chaudhari, YugabyteDB

Thursday August 13, 2026 10:55 - 11:20 KST

An agent processes a payment, hits a timeout, and retries. Now the payment has been charged twice. The model didn’t hallucinate. The workflow did exactly what it was told. The problem is that nobody designed the agent to be safe under retry.

This is a distributed systems problem.

When agents read data, take actions, and write results back, correctness depends on how state is managed across steps. Under retries or concurrent execution, the same workflow can produce conflicting outcomes.

This talk shows how to build stateful AI agents using the Model Context Protocol with a PostgreSQL-compatible distributed database. Instead of treating memory as embeddings, we treat it as structured, transactional state.

You will learn how to design MCP tools for database operations, manage multi-step workflows, and handle failure modes such as retries and idempotency. We will also explore consistency tradeoffs in distributed systems.

The session ends with concrete patterns for building reliable agents, including idempotent tools and safe retry design.

Speakers

Nasiullha Chaudhari

Developer Engagement Manager, YugabyteDB

Nasiullha Chaudhari works as a Developer Engagement Manager at YugabyteDB, focusing on AI systems, distributed databases, and cloud-native architectures. He works on real-world AI agent systems and focuses on what it takes to run them reliably in production.

He is a Docker Captain and an international speaker who has spoken at developer and infrastructure conferences globally. He shares practical insights through his YouTube channel with 180K+ subscribers and with 70K+ followers on LinkedIn

... Read More →

Thursday August 13, 2026 10:55 - 11:20 KST
Orchid 2

Building with MCP

11:25 KST

Building and Taming an MCP Server for Multi-Cloud Vibe Computing - Seokho Son, ETRI

Thursday August 13, 2026 11:25 - 11:50 KST

In early 2025, as MCP adoption grew, we built our first MCP server for Cloud-Barista, an Apache 2.0 multi-cloud project I maintain. We started with a simple approach: feed REST API docs to an LLM, ask it to generate a server, and connect it to Cloud-Barista.

It worked. Users could provision cloud infrastructure across 10 providers, including AWS, Azure, GCP, Alibaba, and NCP, through LLM clients. It felt like an early glimpse of the Vibe Computing I had imagined.

But the first success was incomplete. The server misused APIs, burned tokens, stopped midway, and sometimes provisioned unintended resources. Imagine an agent creating 1,000 VMs with expensive GPUs by mistake. The real work began when we had to feed it better context and tame it with clearer tool boundaries, workflows, and controls.

This made Multi-Cloud Vibe Computing more concrete. It showed that a useful MCP server needs more than API coverage: context design, tool boundaries, workflow guidance, and safety controls.

This session shares lessons from building and taming an MCP server for a real-world system. It is a hands-on story of learning through mistakes and turning an API wrapper into a useful MCP interface.

Speakers

Seokho Son

Special Fellow and Principal Researcher, CNCF Ambassador, ETRI

Dr. Son is a Special Fellow and Principal Researcher at the Electronics and Telecommunications Research Institute (ETRI), South Korea's national research institute. He develops systems and algorithms for cloud and cloud native computing in national projects. As a CNCF Ambassador... Read More →

Thursday August 13, 2026 11:25 - 11:50 KST
Orchid 1

Building with MCP

11:25 KST

From Legacy To Agentic AI - Seoyul Yoon, AAIF Community Seoul

Thursday August 13, 2026 11:25 - 11:50 KST

What does it take to bring a company's legacy systems into the AI era?

Hand-coding tool functions for every backend is not sustainable; maintenance costs grow exponentially as the number of services increases. We solved this with a combination of open source projects.

Given a single OpenAPI spec, the system automatically converts endpoints into MCP Tools, a Kubernetes Operator provisions and manages the MCP server, and a LangGraph + deepagents-based Agent talks to internal systems on top, with Agent Skills (SKILL) shaping how that agent behaves.

This session shares how we selected and composed five open source projects, along with the real-world challenges we hit along the way: multi-provider OAuth, custom Keycloak token verification, per-backend header injection, transport-naming inconsistencies across MCP clients, and rewriting auto-generated tool descriptions to fit the LLM.

Not a finished solution, but a practitioner's account showing that turning legacy systems into AI-ready interfaces is entirely achievable with open source.

Speakers

Seoyul Yoon

Organizer | Platform Engineer, AAIF Community Seoul

I am an AAIF Community Seoul organizer and platform engineer focusing on bridging the gap between legacy enterprise systems and the Agentic AI era. As a passionate advocate for the open-source ecosystem and an active member of Cloud Native Community Korea, I explore the intersection... Read More →

From Legacy to Agentic AI pptx

Thursday August 13, 2026 11:25 - 11:50 KST
Orchid 2

Building with MCP

11:55 KST

From 40 Tools To 14: A Practical Framework for MCP Tool Curation - Nimit Savant & Gokul K S, DevRev

Thursday August 13, 2026 11:55 - 12:20 KST

We built an MCP server exposing 40+ operations. Agents misused most of them. Hybrid search returned only IDs with no context. get_issue prefixed every field with redundant key-value labels, burning tokens without helping the LLM. We had write tools with no corresponding read tools. Custom field schemas varied wildly across organizations, causing unpredictable bloat.
We cut to 14 tools. Agent precision improved dramatically. But deciding which 14 - and how to design them - required building a framework we wish had existed when we started.
This talk shares that framework as an open, reusable methodology any MCP server author can apply: how to audit which tools agents actually select vs. misuse, how to score agent success rate per tool, how to identify tools that confuse rather than help, how to structure response shapes for minimal token cost and maximum agent comprehension, and how to design progressive disclosure so capability scales without overwhelming context.
Every team building an MCP server faces this decision. We'll give them a starting point so they don't have to learn it the hard way.

Speakers

Nimit Savant

Developer Evangelist, DevRev

I love to talk about Agentic AI and B2B Developer Advocacy and strategies

Gokul K S

Member of Technical Staff, DevRev

Computer engineer with 3 years of experience in backend systems and currently exploring the agentic space.

Thursday August 13, 2026 11:55 - 12:20 KST
Orchid 1

Building with MCP

13:50 KST

Who Watches the Watchmen? Safe AI-Agent Failover Via MCP and CRDs - Phuong Bac Ta, Research Center for Distributed Cloud and Networking, SSU, South Korea & Vitumbiko Mafeni, CNLAB | SSU IISTRC

Thursday August 13, 2026 13:50 - 14:15 KST

Giving an AI agent access to a Kubernetes cluster sounds powerful — until it runs the wrong command. The real challenge is not connecting an LLM to a cluster, but constraining what it can do, enforcing correctness, and keeping a human meaningfully in the loop.
This session presents a blueprint for safe, auditable MCP-powered operations through a real use case: an AI-assisted failover system for Kubernetes. Instead of letting an agent call cluster APIs directly, we place a Failover MCP Server in front of the cluster and expose only discrete, permission-scoped tools for observation and controlled action.
Beneath that reasoning layer, a Kubernetes Operator serves as the enforcement point. CRDs such as FailoverPolicy and DisasterRecoveryPlan encode failover semantics, validate requested actions, and ensure execution remains deterministic and policy-compliant. Sensitive actions are held behind a requireApproval setting in the Agent manifest until an operator explicitly approves the next step.
The talk closes with lessons on where LLM reasoning helps during incidents and why Operator-controlled execution still matters in high-risk workflows.

Speakers

Vitumbiko Mafeni

Research Engineer, Research Center for Distributed Cloud and Networking

I am a Research Engineer at the Research Center for Distributed Cloud and Networking, SSU, South Korea, specializing in cloud-native technologies for AI, edge computing, and 5G. I actively contribute to and engage with open-source projects, collaborating with the community to explore... Read More →

Phuong Bac Ta

Research Engineer, Distributed Cloud and Networking Research Center, SSU-IISTRC

Phuong Bac Ta is a Research Engineer at the Research Center for Distributed Cloud and Networking, SSU, South Korea. He works on cloud-native platforms, distributed systems, and Agentic AI for operations, with a focus on observability, automated failover, and resilient infrastructure... Read More →

Thursday August 13, 2026 13:50 - 14:15 KST
Orchid 2

Building with MCP

14:50 KST

Stop Wrapping APIs: Building Structured Execution Boundaries With MCP for Incident Triage - Sunyoung Park, KC-ML2

Thursday August 13, 2026 14:50 - 15:15 KST

Most teams start with MCP by exposing existing APIs as thin tool wrappers. We did too. However, we quickly realized that for complex operations-like managing GPU clusters and infrastructure health-simply exposing more tools doesn't lead to better automation; it leads to LLM confusion. The real challenge is defining the right reasoning and execution boundary.

In this talk, we share our journey of moving beyond simple API exposure to building MCP servers that act as a sophisticated operational layer. We'll dive into how we transformed fragmented signals into 'Structured Guidance' by embedding domain heuristics and workflow context directly into the MCP layer.

Attendees will learn:
- how to recognize when MCP is acting as a thin wrapper versus a real workflow boundary
- how to design MCP on top of existing operational or management systems
- how to turn fragmented tools, signals, and internal APIs into structured guidance for real-world workflows

This session is a practical story about where MCP becomes more than an integration layer: when it starts acting as the execution boundary for real-world operational decisions.

Speakers

Sunyoung Park

Research Engineer, KC-ML2

I am a Research Engineer at KC-ML2, working on large language models, RAG, and applied AI systems. My work focuses on building practical LLM applications and operational AI workflows for real-world use cases.

Stop Wrapping API Sunyoungpark, KC ML2 pdf

Thursday August 13, 2026 14:50 - 15:15 KST
Orchid 1

Building with MCP

16:45 KST

From CRDs to Conversations: Simplifying Chaos Engineering With MCP - Pritesh Kiri, Harness

Thursday August 13, 2026 16:45 - 17:10 KST

Imagine telling your system, “Simulate a pod failure on the payments service,” or asking, “What chaos experiments have we run on service X in the last 30 days?” This talk covers a practical approach to using the Model Context Protocol (MCP) with LitmusChaos. The goal is to move away from manual YAML configuration and CRD lookups by using a natural language interface. I'll demonstrate how this MCP setup works and how it changes the workflow for designing and running resilience tests.

This session introduces Chaos Engineering and explores how MCP makes it more accessible. By replacing YAML and dashboards with human language, we’re lowering the barrier to entry for chaos engineering. Resilience testing becomes accessible to QA, product, and on-call teams, not just platform experts. Whether or not you’re currently using Litmus, this talk will provide a roadmap for building your own chaos copilot and a glimpse into a future where resilience is everyone’s responsibility.

Speakers

Pritesh Kiri

Pritesh Kiri, Harness

Pritesh is the DevRel Engineer at Harness and community manager and maintainer of the LitmusChaos Community. He is also the Head of Community at ReactPlay, leading the ReactPlay Bangalore chapter. He has a strong background as a Developer Advocate, leading tech communities and fostering... Read More →

Thursday August 13, 2026 16:45 - 17:10 KST
Orchid 2

Building with MCP

10:40 KST

From API To Agent: Building a Video Intelligence MCP Server and Plugin Ecosystem - James Le, TwelveLabs

Friday August 14, 2026 10:40 - 11:05 KST

Grand Ballroom 2 + 3

Video intelligence is an unusual MCP workload. Operations are asynchronous and long-running (indexing a 30-minute video takes minutes, not milliseconds), inputs span local files and remote URLs, and the tool surface is wide; search, analysis, embeddings, and entity recognition each carry distinct parameter shapes and response patterns.

When we set out to build a production MCP server for TwelveLabs' video understanding platform, these constraints became a useful stress test for the protocol itself. This talk traces the builder's journey from first commit to published npm package (twelvelabs-mcp), covering the decisions that shaped a 19-tool MCP server and the patterns that emerged along the way.

Attendees will leave with concrete patterns for building MCP servers around API-first platforms (particularly those with async workflows, multimodal inputs, and wide tool surfaces), along with a clear picture of how MCP servers can evolve into full agent plugins.

Speakers

James Le

Head of Developer Experience, TwelveLabs

James Le is currently leading Developer Experience at Twelve Labs, a startup building foundation models for video understanding.

Previously, he worked at MLOps startups Superb AI and Snorkel AI and taught production ML content with Full Stack Deep Learning.

He is also the host of Datacast, a podcast following the narrative journey of founders, operators, and investors in the data and AI infrastructure space to unpack the careers that they have built... Read More →

Friday August 14, 2026 10:40 - 11:05 KST
Grand Ballroom 2 + 3

Building with MCP

10:40 KST

The 5 Wrong Reasons to Build an MCP Server (And What to Do Instead) - Daniel Oh, Red Hat

Friday August 14, 2026 10:40 - 11:05 KST

MCP brings structure and standardization to how LLMs interact with tools and resources—but that power comes with cost. We’ve built multiple MCP servers across different use cases, and not all of them should have existed.
This session distills hard-earned lessons from real-world implementations: where MCP created long-term leverage, where it introduced unnecessary complexity, and where a direct API call would have shipped faster and cleaner. We’ll share a clear evaluation checklist you can use before starting your next build—so you choose MCP intentionally, not reflexively.

Speakers

Daniel Oh

Senior Principal Developer Advocate, Red Hat

Java Champion, CNCF Ambassador & TAG DevEX Co-Chair, AAIF Ambassador, Microsoft MVP, Developer Advocate, Technical Marketing, Keynote Speaker, Published Author

Friday August 14, 2026 10:40 - 11:05 KST
Orchid 1

Building with MCP

11:40 KST

From Chaebol to Cloud-Native: MCP Agent Platforms Inside Korea's Manufacturing Giants - Yogesh Sardana, Independent

Friday August 14, 2026 11:40 - 12:05 KST

Korea's industrial conglomerates—chaebols like Samsung, SK Hynix, Hyundai, LG, and POSCO—operate the most sophisticated manufacturing ecosystems on the planet. Behind the scenes, each utilizes thousands of highly proprietary, heavily siloed Operational Technology (OT) and Information Technology (IT) systems resulting from decades of organic growth and acquisitions. Currently, engineers waste weeks manually extracting, normalizing, and correlating data from these isolated environments before any advanced AI analysis can even begin. This session explores the transformative role of the Model Context Protocol acting as a universal, cloud-native translation layer. We will reveal how manufacturing giants are utilizing Kubernetes-hosted MCP platforms to seamlessly bridge legacy industrial control systems with modern AI agents, radically accelerating industrial intelligence.

Speakers

Yogesh Sardana

AI, Cloud Engineering Leader & Researcher, Independent

Friday August 14, 2026 11:40 - 12:05 KST
Orchid 2

Building with MCP

13:35 KST

Building and Testing MCP Servers With the Inspector, Conformance Suites, and Property-Based Testing - Navin Pai, StackGen

Friday August 14, 2026 13:35 - 14:00 KST

MCP gained popularity because it was as easy as building a REST API. Infact, many might say, building an MCP Server is a bit too easy. Shipping a broken MCP server into a pool of a hundred others is easy but shipping one that actually behaves correctly under adversarial clients, malformed inputs, and edge-case tool schemas is hard.

Devs have already built tens of thousands of MCP servers, and recent spec revisions have focused on richer tool annotations, structured tool outputs, and clearer security best practices, all of which introduce new failure modes to test for.

This session covers a complete testing pyramid for MCP servers: using the official MCP Inspector for interactive tracing, writing conformance tests against the JSON Schema tool definitions, and applying property-based testing (with tools likeHypothesis in Python or fast-check in TypeScript) to fuzz tool inputs and surface schema violations before clients do. We'll also walk through how to set up a CI pipeline that runs your MCP server against a spec conformance suite on every pull request, and how to lint tool descriptions for ambiguity that could confuse real LLM clients.

Speakers

Navin Pai

Director of Engineering, StackGen

Navin is a Founding Engineer at OpsVerse. You'll often find him on the internet, getting into flamewars about observability, large scale system design, and open source software

mcp test slides pdf

Friday August 14, 2026 13:35 - 14:00 KST
Orchid 1

Building with MCP

13:35 KST

Why We Made Our AI Agent Platform a Codebase Before Adding MCP - Navtej Reddy, Observe.ai

Friday August 14, 2026 13:35 - 14:00 KST

Grand Ballroom 2 + 3

Six months ago, building a voice AI agent on our platform meant clicking through a UI. This meant editing prompts, dragging conversation flows, hooking up tools with no audit, no rollback, no review. To make the platform work better with MCP, we moved everything to a Git-backed harness. Each agent is now its own repo with skill folders and an agent.md capturing the agent's custom instructions and unique nuances, so when a customer points Cursor or Claude at it via MCP, the AI picks up that context before making any changes.

This talk covers:
(1) the org-change journey from clickops to version control
(2) the sandboxing model, how MCP safely exposes Git's branch model (dual read/write endpoints, tool-layer branch protection, SSO-derived org scoping)
(3) the two-stage CI on every PR, MCP-driven changes ride the same rails as human-authored ones, with simulations followed by automated evaluations
(4) the closed-loop flow that ties it all together, a user files an issue with a test scenario on an agent's page, the sandboxed AI makes the change, validates it, and submits a PR for review using MCP.

Speakers

Navtej Reddy

Software Engineer 2, Observe.ai

Navtej Reddy is a software engineer at Observe AI, where he built the flow-based voice agent framework that powers 10,000+ daily customer calls and led the MCP integration described in this talk. He's also a Springer (2025) author on AI-driven incident debugging. CS graduate of PES... Read More →

Friday August 14, 2026 13:35 - 14:00 KST
Grand Ballroom 2 + 3

Building with MCP

13:35 KST

Your MCP Server Behaves Differently in Every Client: A Cross-Client Field Guide for Server Authors - Tanisha Sharma, Bolna & Animesh Pathak, Harness

Friday August 14, 2026 13:35 - 14:00 KST

Same MCP server. Same prompt. Three different IDEs. Three different outcomes — and one of them is silently wrong.

After documenting a production MCP server across Cursor, Claude Desktop, and Windsurf, the speaker has the war stories. Tool descriptions one client truncates and another expands. Resource limits that vary by 10x. Notification semantics that work in one host and silently no-op in another. OAuth flows that route through different dances depending on the client. Session-lifetime assumptions that turn into "why did my context vanish?" support tickets.

This talk is a field guide, organized by client, with the actual diffs server authors should care about. Live side-by-side traces of the same tool call across three clients, showing where each one quietly diverges from the spec — and the small defensive changes (in tool naming, description length, error semantics) that make a single server work the same way in all three.

Closes with a proposal: a "client compatibility matrix" the MCP ecosystem should publish and maintain, modeled on Can I Use for the web.

For MCP server authors who have only ever tested in one client.

Speakers

Animesh Pathak

DevRel Engineer, Harness

I'm Animesh Pathak - a Developer Relations Engineer currently at Harness, focused on Database DevOps, APIs, testing, and open-source innovation. Previously, I worked at Keploy where I evangelized eBPF-based testing tools.

Tanisha Sharma

AI DevRel Engineer, Bolna

Tanisha is an AI Developer Advocate specializing in production multi-agent systems. Also a private pilot. Both pursuits taught her the same lesson: know when to trust automation and when human judgment matters most.

Friday August 14, 2026 13:35 - 14:00 KST
Orchid 2

Building with MCP

14:05 KST

Closing the Context Gap: Making Your APIs Agent-Ready - Aanchal Mishra, Postman & Ali Mustafa Shaikh, Pieces AI

Friday August 14, 2026 14:05 - 14:30 KST

Traditional AI implementation relies on "tool sprawl": manually wrapping every API action into custom functions. This creates a maintenance burden where prompts swell, tokens vanish, and agents hallucinate under the weight of excessive choice. At Postman, we’ve shifted the paradigm: instead of teaching agents how an app works, we provide them with structured context they already understand through the MCP.

This session moves beyond theory to demonstrate a live "AI Readiness" workflow using Postman’s native Git integration. We will pit a well-defined OpenAPI schema against a poorly designed one to visualize the "Context Tax" - showing how architectural debt leads to 2x higher token usage and fumbled execution. By leveraging Postman’s MCP Server generator and CLI SDKs, I’ll demonstrate how to transform static documentation into active "code skills" that agents like Claude can navigate autonomously. Attendees will learn to build APIs that don't just return data, but serve as high-fidelity maps for the next generation of autonomous agents.

Speakers

Ali Mustufa Shaikh

Senior Developer Advocate, Pieces AI

I empower developers to overcome traditional education barriers, building their confidence for professional success. Through technical training at leading organizations - including Rakuten, Infosys Deloitte and Open Dealer Exchange I've guided professionals worldwide in Google Cloud... Read More →

Aanchal Mishra

Developer Advocate, Postman, Postman

Aanchal is a Developer Advocate at Postman specializing in Agentic Workflows, API Literacy, and Developer Education. With 5+ years of experience, she has designed global learning paths reaching thousands of developers and delivered over 150 technical workshops across 35+ cities. A... Read More →

Friday August 14, 2026 14:05 - 14:30 KST
Orchid 1

Building with MCP

14:05 KST

Self-Improving MCP Agents - Kemal Elmizan, GoTo Company

Friday August 14, 2026 14:05 - 14:30 KST

Grand Ballroom 2 + 3

Most MCP systems today are static at runtime. We define tools, expose schemas and rely on prompts to guide behavior, then hope the system remains reliable after deployment.

In practice, MCP-based systems drift. Agents repeatedly misuse tools, call inefficient sequences or fail in predictable ways. Tool descriptions become outdated. Context grows noisy. Human operators step in to correct outcomes, but those corrections are rarely captured or reused. MCP standardizes how agents connect to tools, but it does not define how systems improve over time.

I would like to explore how to build MCP systems that go beyond execution by introducing feedback loops on top of the protocol. By combining tool call history and observability, we can build systems that identify their own weaknesses and suggest improvements safely.

The session will cover practical patterns:
- Detecting repeated tool misuse and failure patterns
- Learning from retries, fallbacks, and human corrections
- Identifying redundant or low-value tool chains
- Designing safe feedback loops with audit logs, versioning, rollback and human approval

Speakers

Kemal Elmizan

Lead Software Engineer, GoTo Company

Hi there! I am Kemal Elmizan, currently working as a Software Engineer at Gojek (GoTo Company). I like building software across the stack and like to understand what's going on beneath the surface. I have extensive experience in backend, web, and android development. I have lectured... Read More →

MCP DevSummit Seoul Kemal Elmizan pdf

Friday August 14, 2026 14:05 - 14:30 KST
Grand Ballroom 2 + 3

Building with MCP

Slides Attached Yes

14:35 KST

Managing Token Usage in MCP Servers Using Code Mode - Bhumika Satpathy, Google

Friday August 14, 2026 14:35 - 15:00 KST

Grand Ballroom 2 + 3

As the ecosystem for the Model Context Protocol (MCP) expands, developers are hitting a familiar wall: token bloat. While MCP provides a powerful standardized interface for LLMs to interact with external data, the "context tax" of verbose tool definitions and massive data payloads can quickly degrade performance and spike costs. To build production-ready agents, we must move beyond basic implementations and embrace advanced orchestration.

This session dives into the architecture of efficient MCP server design, focusing on the "Code Mode" technique. We will explore how to shift the heavy lifting from the LLM’s reasoning space to the server’s execution environment. Instead of forcing the model to process raw, unrefined data, "Code Mode" empowers the LLM to generate and ship logic—miniature, execution-ready scripts—directly to the MCP server. This approach minimizes round-trip latency and drastically reduces the input tokens required for complex data manipulation.

Speakers

Bhumika Satpathy

Senior Software Engineer, Google

I am a Senior Software Engineer at Google and have been working with the MCP Platform team which helps to ease out creation and deployment of MCP Servers for developers within Google. We have solved multitude of challenges that users have faced and explored multiple techniques in... Read More →

Friday August 14, 2026 14:35 - 15:00 KST
Grand Ballroom 2 + 3

Building with MCP

14:35 KST

Operating an AI Infrastructure Through MCP Apps on Agents - HyounKyoung Moon, Lablup

Friday August 14, 2026 14:35 - 15:00 KST

GPU infrastructure has traditionally been operated through CLIs, dashboards, and a patchwork of admin tools. Each task — checking cluster state, allocating resources, launching sessions — forces the operator to switch context and stitch results together manually.

MCP changes the surface of this work. By exposing infrastructure operations as MCP tools, an agent can carry out cluster tasks on the operator's behalf. And with MCP Apps (SEP-1865), the agent doesn't just respond in text — it renders interactive UIs inline, so the operator can see the cluster, review the agent's plan, and approve actions visually within the same conversation.

This talk shows how an agent embedded in an MCP host can manage GPU infrastructure efficiently by combining:

- **Visual control via MCP Apps** — the agent renders cluster status views, resource allocation charts, and confirmation cards inline. The operator sees the infrastructure, reviews the plan, and clicks to approve.
- **Session-level control via MCP** — the agent creates, inspects, and modifies compute sessions through MCP tool calls.
- **Human-in-the-loop by design** — visual checkpoints make every consequential action explicit

Speakers

HyounKyoung Moon

AI Agentic Lead, Lablup

AI Product Engineer who builds AI Agent Platform and AI-first products across diverse stacks

Friday August 14, 2026 14:35 - 15:00 KST
Orchid 2

Building with MCP

14:35 KST

Two Audiences, One Markdown File: Writing MCP Docs an Agent Can Actually Use - Tanisha Sharma, Bolna & Jyoti Bisht, Independent

Friday August 14, 2026 14:35 - 15:00 KST

When an MCP server exposes documentation.search and documentation.fetch, its docs site quietly acquires a second reader: the agent. And the agent is not a small human. Humans want narrative tutorials; agents want flat, deduplicated, single-source-of-truth pages. Humans skim; agents tokenize. Humans tolerate ambiguity; agents hallucinate from it.

This talk is a field report from rewriting an MCP server's documentation to serve both audiences from one markdown source. Concrete before/after pages, real agent traces from the SuprSend MCP server (used as a case study not a pitch), the five rewrite rules that actually moved the needle on hallucination rates, and the surprising downstream effect: the human-facing docs got better too. Every rule generalizes to any MCP server with public docs.

Closes with two open questions the audience is invited to argue back at: should agent-facing docs be a separate channel? Should MCP add a "documentation" primitive at the protocol level?

For DevRels, technical writers, and MCP server maintainers who already exposed their docs as a tool or are about to.

Speakers

Jyoti Bisht

DevRel Engineer, Independent

Tanisha Sharma

AI DevRel Engineer, Bolna

Tanisha is an AI Developer Advocate specializing in production multi-agent systems. Also a private pilot. Both pursuits taught her the same lesson: know when to trust automation and when human judgment matters most.

Friday August 14, 2026 14:35 - 15:00 KST
Orchid 1

Building with MCP