A service for getting AI-generated answers through a network where different providers compete to supply and verify each result. It covers tasks such as weather forecasts, climate data, deepfake detection, text generation, image generation, and embeddings.

Use it to query weather and climate information, detect AI-made content or deepfakes, generate text or images, create embeddings, and monitor signals in areas such as politics or technology.

It gives an agent a way to request AI results with checks on their reliability, instead of depending on one unverified provider. Some requests use USDC payments.

How telegraphprotocol/telegraph-mcp configures Claude Code and Codex

Reuse

Borrowing it

Nothing to install: this file belongs to telegraphprotocol/telegraph-mcp. 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/telegraphprotocol/telegraph-mcp/main/.agents/skills/telegraph/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/telegraphprotocol/telegraph-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/telegraphprotocol/telegraph-mcp/telegraph/github.svg)](https://agentmods.dev/skills/telegraphprotocol/telegraph-mcp/telegraph)

Your own site

<a href="https://agentmods.dev/skills/telegraphprotocol/telegraph-mcp/telegraph"><img src="https://agentmods.dev/badge/skills/telegraphprotocol/telegraph-mcp/telegraph/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/telegraphprotocol/telegraph-mcp/telegraph"><img src="https://agentmods.dev/badge/skills/telegraphprotocol/telegraph-mcp/telegraph.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 112 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,078 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	$0.00112	$0.01078
Opus 5.5	$0.00045	$0.00431
Sonnet 5.5	$0.00022	$0.00216
Haiku 4.5	$0.00011	$0.00108

Measured 5d ago against content hash 193d12a6b3b4, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

telegraph 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 5d 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

telegraph — 100% identical, 178 lines differ

.agents/skills/telegraph/SKILL.md · 72 lines

How it starts

The opening of the file, as written. The whole thing — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Telegraph

Telegraph is a network of miners (APIs and models run by different people) that answer questions by intent. Every epoch the network checks each intent's miners and ranks them, and an ask goes to the best-ranked live miner. Asks are paid in USDC, usually $0.01.

Tools

Tool	Cost	Use it to
`telegraph_ask`	~$0.01	Ask a question. Optional `intent` and `params` make it exact
`telegraph_ask_miner`	that miner's price	Ask one miner the user chose, or call one of its endpoints directly
`telegraph_find_intents`	free	Find the intent for a kind of question
`telegraph_intent`	free	See an intent's kind, params, answer fields and top miners
`telegraph_find_miners`	free	List an intent's miners with rank, score and price, or search miners by words
`telegraph_ranking`	free	The latest ranking for an intent, or for all
`telegraph_account`	free	Wallet USDC and ETH, and the escrow balance
`telegraph_deposit`	gas	Move wallet USDC into escrow. Confirm the amount with the user first
`telegraph_docs`	free	How payments, intents, ranking and errors work

How to use it

A plain question is enough: telegraph_ask(question="What is the BTC price in USD?"). The node finds the intent and the miner.
To be exact, find the intent and its params first, then ask with them: telegraph_find_intents(search="weather") → telegraph_intent(intent="WEATHER_CHECK_TEMPERATURE") → telegraph_ask(intent="WEATHER_CHECK_TEMPERATURE", params={"location": "Lahore"}).
The answer comes back in the intent's fields (answer), with the miner that answered and the payment receipt. Tell the user which miner answered.
An intent with no ranking yet is answered by one of the miners that declare it. telegraph_intent says when that is the case.

Payments

Escrow first: if the wallet has a Telegraph escrow balance, each ask is signed against it and deducted at the epoch close. A failed ask is never billed.
x402 fallback: otherwise the ask is paid from the wallet's USDC. If it then fails, the amount is credited to the user's escrow.
telegraph_account shows the balances. telegraph_deposit tops up escrow, but only after the user confirms the amount.
The private key stays in the MCP server's process. It never appears in tool inputs, outputs or model context.

Read the full file on GitHub · 72 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.

5d ago Changed · -80 lines · -10 tokens per session 193d12a6b3b4
2mo ago First seen · 152 lines · 122 tokens per session scan A 36fae463b7c1

Subscribe to this mod's changes

telegraph is a skill published in the GitHub repository telegraphprotocol/telegraph-mcp (0 stars, last pushed 4d ago), licensed MIT. It adds 112 tokens to every session and 1,078 once invoked, about $0.0004 per session on Opus 5.5. 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 2026-08-31.

Data and AI

telegraph next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
telegraphtelegraphprotocol/telegraph-mcp	Skill	0	4d ago	MIT	A	112	Claude Code, Codex
agent-platform-model-registrygoogle/skills	Skill	22k	yesterday	Apache-2.0	A	60	Claude Code, Codex
foundry-config-setupmicrosoft/agent-framework	Skill	15k	yesterday	MIT	A	65	Claude Code, Codex
google-cloud-solution-agentic-analytics-spark-knowledge-cataloggoogle/skills	Skill	22k	yesterday	Apache-2.0	A	132	Claude Code, Codex
training-checkwanshuiyin/Auto-claude-code-research-in-sleep	Skill	19k	3d ago	MIT	A	35	Claude Code
nemo-automodel-launcher-configNVIDIA/skills	Skill	3.9k	yesterday	Apache-2.0	A	30	Claude Code
finetuningmicrosoft/skills	Skill	3.2k	yesterday	MIT	A	132	Claude Code

telegraph-mcp: Skill for Claude Code