nlweb-mcp-server

nlweb-mcp-server is a skill for Claude Code from OrcaQubits/agentic-commerce-skills-plugins. It costs 89 tokens per session (2,372 once invoked), scanned A, original, MIT.

A guide for exposing NLWeb through MCP, a standard way for AI applications such as ChatGPT or Claude to call tools. It covers the JSON-RPC endpoint, available tools, and protocol version handling.

In plain words
What is it for?
Use it to connect AI agents to NLWeb, implement or consume its `/mcp` endpoint, and work with the ask, list-sites, and who operations.
Why use it?
It removes the need to design a separate connection between NLWeb and each AI client, while highlighting compatibility details that can change between releases.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: reads .claude/ paths; mentions Claude Code.

Part of the nlweb-protocol plugin — 13 skills, 1 agent shipped together

Good fit Use it to connect AI agents to NLWeb, implement or consume its /mcp endpoint, and work with the ask, list-sites, and who operations.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/orcaqubits/agentic-commerce-skills-plugins/nlweb-mcp-server
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add OrcaQubits/agentic-commerce-skills-plugins --skill nlweb-mcp-server
Clone the repo
git clone --depth 1 https://github.com/OrcaQubits/agentic-commerce-skills-plugins

Made for: Claude Code.

Or install nlweb-protocol, the plugin that ships this one along with the rest of its 13 skills, 1 agent.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for nlweb-mcp-server

README.md
[![agentmods](https://agentmods.dev/badge/skills/orcaqubits/agentic-commerce-skills-plugins/nlweb-mcp-server/github.svg)](https://agentmods.dev/skills/orcaqubits/agentic-commerce-skills-plugins/nlweb-mcp-server)
Your own site
<a href="https://agentmods.dev/skills/orcaqubits/agentic-commerce-skills-plugins/nlweb-mcp-server"><img src="https://agentmods.dev/badge/skills/orcaqubits/agentic-commerce-skills-plugins/nlweb-mcp-server/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for nlweb-mcp-server

Your own site · 80×15
<a href="https://agentmods.dev/skills/orcaqubits/agentic-commerce-skills-plugins/nlweb-mcp-server"><img src="https://agentmods.dev/badge/skills/orcaqubits/agentic-commerce-skills-plugins/nlweb-mcp-server.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 89 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,372 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00089 $0.02372
Opus 5 $0.00044 $0.01186
Sonnet 5 $0.00018 $0.00474
Haiku 4.5 $0.00009 $0.00237

Measured 2d ago against content hash a72a9a40e6f1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-16, from the pricing page.

Security

Grade A, and why

nlweb-mcp-server scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

nlweb-protocol/skills/nlweb-mcp-server/SKILL.md · 198 lines

How it starts

The opening of the file, as written. The whole thing — 198 lines — stays where its author put it; the contents beside it link to each section on GitHub.

NLWeb MCP Server

Before writing code

Fetch live spec:

  1. Fetch https://github.com/nlweb-ai/NLWeb/blob/main/docs/nlweb-rest-api.md (covers /mcp route alongside /ask).
  2. Read AskAgent/python/webserver/mcp_wrapper.py in the live repo for the exact JSON-RPC method list and tool schemas — these change between releases.
  3. Fetch https://github.com/nlweb-ai/NLWeb/blob/main/docs/nlweb-chatgpt-integration.md for the ChatGPT-specific wiring.
  4. Fetch https://modelcontextprotocol.io/specification/ — it redirects to the current revision. Read the transport rules and the changelog there; never assume a revision from memory.
  5. Web-search the latest release notes for any MCP-related changes — the wrapper file's own docstring warns "Backwards compatibility is not guaranteed."

Conceptual Architecture

How NLWeb Implements MCP

NLWeb is already an MCP server out of the box — same code, second binding. The /mcp route in webserver/routes/mcp.py accepts JSON-RPC 2.0 requests and re-uses the same NLWebHandler pipeline as /ask. No separate process, no extra config.

Routes

Route Method Purpose
/mcp POST, GET Main JSON-RPC endpoint
/mcp/{path} POST, GET Path-scoped variant
/mcp/health GET Liveness check

MCP Protocol Revision

NLWeb advertises a dated MCP revision (e.g. 2026-07-28) and the server name nlweb-mcp-server. Never hard-code a revision string — the one your build ships is whatever the installed NLWeb release advertises, and the one your client should send is whatever the spec currently defines.

Resolve it at implementation time:

  1. Fetch https://modelcontextprotocol.io/specification/ for the current revision.
  2. Read the installed NLWeb's mcp_wrapper.py for the revision it advertises.
  3. If they differ, target the older of the two and note the gap — MCP revisions are not silently backward-compatible.

The transport has changed shape across revisions. The 2026-07-28 core is stateless: the initialize / notifications/initialized handshake and the Mcp-Session-Id header were removed from Streamable HTTP. Code written against a handshake-era revision will not match a stateless server, and vice versa — so confirm which model applies before writing client code.

Read the full file on GitHub · 198 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 198 lines · 89 tokens per session scan A a72a9a40e6f1

Subscribe to this mod's changes

nlweb-mcp-server is a skill published in the GitHub repository OrcaQubits/agentic-commerce-skills-plugins (39 stars, last pushed 2d ago), licensed MIT. It adds 89 tokens to every session and 2,372 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-15.

Related

Other skills, from other repositories

archestra-dev-interactions-migrations

Use BEFORE writing or running any Drizzle migration that touches the interactions table (or any other very large, write-hot table). The interactions table is the platform's biggest, append-heavy table — every LLM proxy call writes a row — so a careless migration can take a write-blocking lock and stall the proxy.…

archestra-ai/archestra · 118 tokens

archestra-dev-llm-providers

Use when adding an LLM provider, changing proxy adapters or provider routes, fixing streaming/tool-call translation bugs, editing model fetchers or model handling, or touching provider credentials/enums and model constants.

archestra-ai/archestra · 49 tokens

archestra-dev-backend

Use when adding or changing Archestra backend routes, models, services, API request/response schemas, endpoint permissions, or OpenAPI/codegen for the generated API client.

archestra-ai/archestra · 40 tokens

debridge

Complete deBridge Protocol SDK for building cross-chain bridges, message passing, and token transfers on Solana. Use when building cross-chain applications, bridging assets between Solana and EVM chains, or implementing trustless external calls.

internet-court/internet-court-skill · 48 tokens

near-intents

Cross-chain token swap integration using NEAR Intents 1Click API. Use when building swap widgets, bridge interfaces, or multi-chain transfers across EVM, Solana, NEAR, TON, Stellar, and Tron.

internet-court/internet-court-skill · 49 tokens

arwp-agent-discovery

Add or repair machine-readable agent discovery and interoperability surfaces for a website. Use when asked to expose llms.txt, AGENTS.md, Agent Skills, ARD, MCP, A2A, WebMCP, OpenAPI, API catalogs, agent-readable sitemaps, or an ARWP site profile. Discover what the site truly supports, prefer upstream standards, and…

dkharlanau/agent-ready-web-profile · 88 tokens