What is mcpkit CLAUDE.md?

A project guide for mcpkit, a Go library used to build MCP servers and clients. It points developers to the right documentation and lists supported commands for testing, security checks, and releases.

Use it to find project structure and detailed guidance, run the supported test targets, perform audits, tidy imports, and prepare version tags.

It gives contributors a clear starting point for understanding the repository and avoids relying on commands or rules that may not match the project’s authoritative workflow.

How panyam/mcpkit configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to panyam/mcpkit. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/panyam/mcpkit/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/panyam/mcpkit

Made for: Claude Code.

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/panyam/mcpkit/claude-md/github.svg)](https://agentmods.dev/instructions/panyam/mcpkit/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/panyam/mcpkit/claude-md"><img src="https://agentmods.dev/badge/instructions/panyam/mcpkit/claude-md/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/panyam/mcpkit/claude-md"><img src="https://agentmods.dev/badge/instructions/panyam/mcpkit/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 8,995 This file is loaded in full into every session.

When invoked 8,995 The same file — it is already loaded in full.

Security scan A 1 finding. 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.

Model	Per session	Once invoked
Fable 5.1	$0.08995	$0.08995
Opus 5.5	$0.03598	$0.03598
Sonnet 5.5	$0.01799	$0.01799
Haiku 4.5	$0.00899	$0.00899

Measured 3d ago against content hash 6484909ae5e8, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

mcpkit CLAUDE.md scanned grade A with 1 finding 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 3d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

by its `Host`, so curl and Claude Code get a 403 too; only a valid bearer token skips it (#1547).

CLAUDE.md · 436 lines

How it starts

The opening of the file, as written. The whole thing — 436 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md — MCPKit

Go library for building production-grade MCP servers and clients.

The agent SDK that used to sit above the protocol here now lives in its own repository, chakra. Nothing in this tree depends on it.

This file is a router. Detail lives beside the code it describes. See Where knowledge lives below before adding anything here.

Quick Commands

make is the supported runner and the only one CI uses. Justfiles mirroring these names exist but are an experiment; make is authoritative when they disagree.

make test              # Core tests (core/server/client/testutil)
make test-auth         # ext/auth sub-module
make test-ui           # ext/ui sub-module
make test-e2e          # E2E tests (auth + apps)
make test-examples     # examples/ orchestrator
make testall           # Everything (9 stages, 21 sub-stages) + Keycloak + HTML report
make audit             # govulncheck + gosec + gitleaks + race
make tidy-all          # Required after touching core/ imports
make tag-push V=vX.Y.Z # Tag root + all sub-modules and push (RELEASING.md; pre-release is vX.Y.Z-bN)
make check-release-workflows V=vX.Y.Z  # Confirm the tag actually triggered its workflows
make check-install V=vX.Y.Z            # go install every tagged command from the proxy (#1488)

Conformance targets (testconf, testconf-client, testconf-tasks-v2, testconf-mrtr, testconf-skills, testconf-events, testconf-stateless, testconf-upstream-audit, refresh-conformance, check-conformance-stale, …) are orchestrated in conformance/Makefile, which also documents each suite's MCPCONFORMANCE_*_PATH. See conformance/NOTES.md for how they are wired and which upstream changes to watch.

Package Layout

Package	Docs
`core/` — Protocol types, typed contexts, session APIs	`core/README.md`, `core/CONSTRAINTS.md`
`server/` — Server, transports, middleware, v1 tasks (frozen)	`server/README.md`, `server/CONSTRAINTS.md`, `server/NOTES.md`
`client/` — Client, transports, reconnection, auth retry	`client/README.md`, `client/CONSTRAINTS.md`
`ext/auth/` — JWT, PRM, OAuth (separate go.mod)	`ext/auth/docs/DESIGN.md`
`ext/tasks/` — SEP-2663 v2 tasks extension (separate go.mod)	`ext/tasks/README.md`
`ext/skills/` — SEP-2640 skills (data-only, enforced)	`ext/skills/NOTES.md`
`ext/ui/` — MCP Apps, Bridge JS, AppHost, ServerRegistry	`docs/APPS_DESIGN.md`, `docs/APPS_HOST.md`, `ext/ui/NOTES.md`
`ext/otel/` — SEP-414 OpenTelemetry adapter	`ext/otel/README.md`, `docs/SEP_414_OTEL.md`
`experimental/ext/events/` — MCP Events protocol; `clients/go/bridge` is the watch-and-act daemon (#1579)	`experimental/ext/events/README.md`, `experimental/ext/events/NOTES.md`, `experimental/ext/events/clients/go/bridge/README.md`
`experimental/ext/agents/` — Server-declared agent discovery (pre-SEP)	`experimental/ext/agents/README.md`, `experimental/ext/agents/NOTES.md`
`experimental/ext/rooms/` — Room bridge: agents call tools web pages offer (#1581)	`experimental/ext/rooms/README.md`, `experimental/ext/rooms/NOTES.md`
`experimental/integrations/roomsevents/` — Room events as SEP-3415, plus the Claude Code channel front end (#1581)	`experimental/integrations/roomsevents/README.md`, `experimental/integrations/roomsevents/NOTES.md`
`experimental/ext/rooms/massrelay/` — `RoomTransport` over massrelay, embedded or WebSocket (separate go.mod)	`experimental/ext/rooms/massrelay/README.md`, `experimental/ext/rooms/massrelay/NOTES.md`
`experimental/ext/rooms/ts/` — `joinToolRoom`, the browser page client for the room bridge (pnpm)	`experimental/ext/rooms/ts/README.md`, `experimental/ext/rooms/ts/NOTES.md`
`experimental/ext/protogen/` — Proto → MCP codegen	`experimental/ext/protogen/docs/DESIGN.md`
`conformance/` — Suite orchestration + audits	`conformance/NOTES.md`
`examples/` — Working examples	`examples/README.md`, `examples/CONVENTIONS.md`, `examples/NOTES.md`
`testutil/`, `tests/e2e/`, `tests/keycloak/` — Helpers and integration tests	`tests/e2e/apps/README.md`

Read the full file on GitHub · 436 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.

3d ago Changed · +27 lines · +646 tokens per session 6484909ae5e8
5d ago Changed · +13 lines · +329 tokens per session deeacbde4307
6d ago Changed · +23 lines · +738 tokens per session 374b2ceedf7a
9d ago Changed · +8 lines · +240 tokens per session c8d1d489adee
13d ago Changed · +11 lines · +264 tokens per session ee3a313bbbfd
15d ago Changed · +10 lines · +239 tokens per session 7dfae72d68b6
16d ago Changed · +21 lines · +374 tokens per session 441fc9059418
1mo ago Changed · +35 lines · +762 tokens per session e2a1c0dbeb8b
1mo ago Changed · -12 lines · -196 tokens per session b3086ef4ed43
1mo ago First seen · 300 lines · 5,599 tokens per session scan A 46e0ef65befa

Subscribe to this mod's changes

mcpkit CLAUDE.md is an instructions file published in the GitHub repository panyam/mcpkit (6 stars, last pushed 2d ago), licensed Apache-2.0. It adds 8,995 tokens to every session, about $0.0360 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 9,715 tokens

mcpkit: Instructions file for Claude Code

Borrowing it

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Makes network callslowCapability

How it starts

CLAUDE.md — MCPKit

Quick Commands

Package Layout

What this file has done since we first saw it

Other instructions, from other repositories

vscode buildNext.instructions.md

next.js AGENTS.md

vscode oss-third-party-notices.instructions.md

langchain AGENTS.md

vscode copilot-instructions.md

deno copilot-instructions.md