api-context

api-context is a skill for Claude Code, Codex from cyanheads/toolkit-mcp-server. It costs 79 tokens per session (11,090 once invoked), scanned A, a copy of api-context, Apache-2.0.

A reference for the shared request context passed to every MCP tool and resource handler.

In plain words
What is it for?
Use it to read request and session details, log domain events, store state, collect additional input, handle cancellation, and add content to responses.
Why use it?
It shows where to access request identity, logging, tenant storage, user input, cancellation, and response enrichment.

Skill for Claude CodeCodex

Part of the toolkit-mcp-server plugin — 32 skills, 1 MCP server shipped together

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.

agentmods
npx agentmods add skills/cyanheads/toolkit-mcp-server/api-context
Any agent
npx skills add cyanheads/toolkit-mcp-server --skill api-context
Clone the repo
git clone --depth 1 https://github.com/cyanheads/toolkit-mcp-server

Made for: Claude Code, Codex.

Or install toolkit-mcp-server, the plugin that ships this one along with the rest of its 32 skills, 1 MCP server.

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 api-context

README.md
[![agentmods](https://agentmods.dev/badge/skills/cyanheads/toolkit-mcp-server/api-context.svg)](https://agentmods.dev/skills/cyanheads/toolkit-mcp-server/api-context)
Your own site
<a href="https://agentmods.dev/skills/cyanheads/toolkit-mcp-server/api-context"><img src="https://agentmods.dev/badge/skills/cyanheads/toolkit-mcp-server/api-context.svg" alt="Measured on agentmods" height="20"></a>
Per session 79 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 11,090 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. Scan, not verified.
Origin 100% copy Near-identical to another mod 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 $0.00079 $0.11090
Opus 5 $0.00039 $0.05545
Sonnet 5 $0.00016 $0.02218
Haiku 4.5 $0.00008 $0.01109

Measured 3d ago against content hash c78158354f33, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

api-context 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.

const response = await fetch(url, { signal: ctx.signal });
Origin

This is a copy

100% identical to api-context — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

skills/api-context/SKILL.md · 815 lines

How it starts

The opening of the file, as written. The whole thing — 815 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Overview

Every tool and resource handler receives a single Context (ctx) argument. It provides request identity, structured logging, tenant-scoped storage, multi-round-trip input collection, and cancellation — all auto-correlated to the current request.

The framework auto-instruments every handler call (OTel span, duration, payload metrics). Use ctx.log for domain-specific logging and ctx.state for storage inside handlers. Use the global logger and StorageService directly only in lifecycle/background code (setup(), services).


Context interface

import type { Context } from '@cyanheads/mcp-ts-core';

interface Context extends RequestContext {
  // Identity & tracing (inherited from RequestContext — see § RequestContext)
  readonly requestId: string;       // Unique per request, auto-generated
  readonly timestamp: string;       // ISO 8601 request start time
  readonly tenantId?: string;       // JWT 'tid' claim; 'default' for stdio and HTTP+MCP_AUTH_MODE=none
  readonly sessionId?: string;      // Mcp-Session-Id (HTTP stateful/auto); undefined elsewhere unless opted in
  readonly traceId?: string;        // Trace containing this handler execution
  readonly spanId?: string;         // The handler's own execution span
  readonly auth?: AuthContext;      // Parsed auth claims (clientId, scopes, sub)
  readonly operation?: string;      // Label for the operation this context belongs to
  readonly extra?: Readonly<Record<string, unknown>>;  // Correlation bag — the one open field

  // Structured logging — auto-includes requestId, traceId, tenantId.
  // Dual-sink: Pino on the server, plus notifications/message to the client.
  readonly log: ContextLogger;

  // Tenant-scoped key-value storage
  readonly state: ContextState;

  // Multi-round-trip input — always present, both eras (see § ctx.requestInput)
  readonly requestInput: RequestInputFn;   // (spec) => never — suspends and asks the caller
  readonly inputs: ContextInputs;          // reader over a retried request's responses

  // List-changed / resource-updated notifications — wired in every handler ctx;
  // delivery is request-scoped (see § list-changed notifications)
  readonly notifyResourceListChanged?: () => void;
  readonly notifyResourceUpdated?: (uri: string) => void;
  readonly notifyPromptListChanged?: () => void;
  readonly notifyToolListChanged?: () => void;

  // Cancellation
  readonly signal: AbortSignal;

  // Raw URI — present only for resource handlers
  readonly uri?: URL;

  // Agent-facing success-path enrichment — accumulates notices, query echo, totals
  // onto the request; reaches structuredContent + content[]. Always present (no-op
  // when no `enrichment` block), strictly typed on HandlerContext<R, E> against the
  // declared fields. Kind-tagged helpers: enrich.notice / .total / .echo.
  readonly enrich: Enrich;

  // Non-text content blocks (image/audio bytes) for the calling model — prepended
  // to content[] after format() runs, never placed in structuredContent. Always
  // present (no-op when never called). Helpers: content.image / .audio; content(block)
  // pushes a raw ContentBlock.
  readonly content: ContentCollect;

  // Opt-in contract resolver — always present (returns {} when no contract is attached
  // or the reason is unknown), strictly typed on HandlerContext<R> against declared reasons.
  recoveryFor(reason: string): { recovery: { hint: string } } | {};
}

Read the full file on GitHub · 815 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. 3d ago First seen · 815 lines · 79 tokens per session scan A c78158354f33

Subscribe to this mod's changes

api-context is a skill published in the GitHub repository cyanheads/toolkit-mcp-server (18 stars, last pushed 11d ago), licensed Apache-2.0. It adds 79 tokens to every session and 11,090 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). It is 100% identical to api-context, differing in 0 lines, and is treated as a copy.

Related

Other skills, from other repositories

build-mcp-server

This skill should be used when the user asks to "build an MCP server", "create an MCP", "make an MCP integration", "wrap an API for Claude", "expose tools to Claude", "make an MCP app", or discusses building something with the Model Context Protocol. It is the entry point for MCP server development — it interrogates…

pproenca/unifi-mcp · 111 tokens

implementation-strategy

Decide how to implement runtime and API changes before editing code. Use when a task changes exported APIs, MCP tool definitions, runtime behavior, or configuration, and you need to choose the compatibility boundary and implementation shape.

pproenca/unifi-mcp · 47 tokens

docs-sync

Audit documentation coverage by comparing implementation against docs/. Use when asked to check doc coverage, sync docs with code, or after significant API surface changes. Produce a report and ask for approval before editing.

pproenca/unifi-mcp · 42 tokens

pr-draft-summary

Generate a PR-ready summary block with branch suggestion, title, and description. Use in the final handoff after moderate-or-larger code changes; skip for trivial or conversation-only tasks.

pproenca/unifi-mcp · 42 tokens

code-change-verification

Run the verification stack (format, lint, typecheck, test) when changes affect runtime code, tests, or build config.

pproenca/unifi-mcp · 31 tokens

typescript

This skill should be used when the user asks to "optimize TypeScript performance", "speed up tsc compilation", "configure tsconfig.json", "fix type errors", "improve async patterns", or encounters TS errors (TS2322, TS2339, "is not assignable to"). Also triggers on .ts, .tsx, .d.ts file work involving type…

pproenca/unifi-mcp · 102 tokens