A guide to authenticating with Sugra API MCP and working within its daily request quota. MCP is a way for an AI client to call external tools; the guide covers API keys, bearer tokens, OAuth, and quota errors.

Use it when setting up a client or handling 401, 429, or missing-key errors.

It helps resolve unauthorized and rate-limit failures while keeping credentials out of code, logs, and chat.

auth-limits — Skill for Claude Code and Codex by Sugra-Systems

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 Sugra-Systems/sugra-api-mcp --skill auth-limits

Clone the repo

git clone --depth 1 https://github.com/Sugra-Systems/sugra-api-mcp

Made for: Claude Code, Codex.

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/skills/sugra-systems/sugra-api-mcp/auth-limits/github.svg)](https://agentmods.dev/skills/sugra-systems/sugra-api-mcp/auth-limits)

Your own site

<a href="https://agentmods.dev/skills/sugra-systems/sugra-api-mcp/auth-limits"><img src="https://agentmods.dev/badge/skills/sugra-systems/sugra-api-mcp/auth-limits/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/skills/sugra-systems/sugra-api-mcp/auth-limits"><img src="https://agentmods.dev/badge/skills/sugra-systems/sugra-api-mcp/auth-limits.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 40 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 506 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.

Model	Per session	Once invoked
Fable 5.1	$0.00040	$0.00506
Opus 5	$0.00020	$0.00253
Sonnet 5	$0.00008	$0.00101
Haiku 4.5	$0.00004	$0.00051

Measured today against content hash 2dabefe6542f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

auth-limits 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 today.

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.

sugra_api_mcp/skills/auth-limits/SKILL.md · 29 lines

What it actually says

Auth and rate limits

Credentials

stdio: set SUGRA_API_KEY (sugra_... from https://app.sugra.ai/settings/billing) in the server process. Catalog tools (search_endpoints, describe_endpoint, list_toolsets, list_sources) work without it. call_endpoint, fetch_data, and the entity tools return a structured missing_api_key error until it is set.
Streamable HTTP (hosted https://app.sugra.ai/mcp or self-hosted): the MCP client sends Authorization: Bearer. That is a raw API key or an OAuth JWT (audience https://app.sugra.ai/mcp, scope sugra:read). Discovery (initialize, tools/list, resources/list, prompts/list, ping) is public. tools/call and resources/read return 401 missing_bearer_token without Bearer. SUGRA_API_KEY on the HTTP process is only a downstream fallback, not a substitute for the client's Bearer.
Downstream API calls use x-api-key. Do not log the key or put it in a skill file, commit, or chat.

Quota

Every plan sees every endpoint. Gating is volume, not surface.

Plan	Requests / day
Free	50
Dev	5,000
Pro	50,000

Some bulk endpoints cost more than 1 request; describe_endpoint agent_hints.bulk_cost warns before the call.

On 401, the credential is missing or invalid - do not retry the same call. On 429 from an MCP tool, wait for the JSON field retry_after (seconds). Direct HTTP to https://sugra.ai also sends X-RateLimit-Limit, X-RateLimit-Remaining, X-RateLimit-Reset, and X-RateLimit-Cost; the MCP tool envelope does not forward those headers. elapsed_ms on a tool error says which timeout fired.

Get a key at https://app.sugra.ai/settings/billing.

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.

today First seen · 29 lines · 40 tokens per session scan A 2dabefe6542f

Subscribe to this mod's changes

auth-limits is a skill published in the GitHub repository Sugra-Systems/sugra-api-mcp (2 stars, last pushed today), licensed MIT. It adds 40 tokens to every session and 506 once invoked, about $0.0002 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 2026-09-11.

DevOps and cloud Security data-platform intelligence-infrastructure llm-tools mcp model-context-protocol

webmcp-nexus

A coding guide for adding WebMCP tools to JavaScript or TypeScript projects. WebMCP lets AI agents call selected application functions through a standard interface.

alibaba/webmcp-nexus · 159 tokens

unblock

Use whenever you need to read a web page, URL, article, documentation page, search result, product page or any live website content. Fetches through UnblockingAPI (unblockfetch, findtemplates) instead of the built-in WebFetch, starting with a plain fetch and rendering with a real browser only when the page needs…

unblockingapi/mcp · 83 tokens

dark-memory

Use for governance, memory, drift detection, and audit trail via dark-memory-mcp. Covers 52 canonical + 3 red-team tools across 16 namespaces: session lifecycle, agentmemory CRUD+search, vibe-flow spec/artifact publish + drift, LLM-as-judge, delegation+mindset, research, observability, error observatory, governance…

Opita-Code/dark-memory-mcp · 353 tokens

driving-unreal

Use when driving an Unreal Engine 5.x editor through the unreal-ai-connection MCP tools — building or populating a level, spawning/transforming actors, authoring materials and material instances, setting up lighting and atmosphere, reconstructing a scene from a reference photo, setting up a sequencer/cinematic shot…

NAJEMWEHBE/unreal-ai-connection · 269 tokens

youtube-transcripts

Read and search YouTube videos through VidWords. Use when the user supplies a YouTube URL, a bare 11-character video id, a youtu.be or Shorts link, or a channel handle, and wants any of: the transcript or subtitles (TXT/SRT/VTT), what a video says about a topic, a quote with a citable timestamp, only the words spoken…

haljishi/vidwords-mcp · 111 tokens

lyrenth-web-reading

Read the content of one or many public web pages through Lyrenth, as clean Markdown instead of raw HTML. Use when the user gives a URL to read, summarize, quote, compare or extract from, or when a link needs to be opened to answer a question.

lyrenth/lyrenth-mcp · 61 tokens