What is syntx-ai-mcp-usage?

Operational guidance for using syntx.ai tools, which let an agent chat with models and work with files, audio, video, designs, and folders.

It helps with syntx.ai authentication, model selection, chat continuation, streaming choices, file uploads, and transcription calls.

It explains behaviors that are not obvious from the tool descriptions, such as choosing model identifiers, handling long requests, and continuing chats.

syntx-ai-mcp-usage — Skill for Claude Code and Codex by ssm82

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 ssm82/syntx-ai-mcp --skill syntx-ai-mcp-usage

Clone the repo

git clone --depth 1 https://github.com/ssm82/syntx-ai-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/ssm82/syntx-ai-mcp/syntx-ai-mcp-usage/github.svg)](https://agentmods.dev/skills/ssm82/syntx-ai-mcp/syntx-ai-mcp-usage)

Your own site

<a href="https://agentmods.dev/skills/ssm82/syntx-ai-mcp/syntx-ai-mcp-usage"><img src="https://agentmods.dev/badge/skills/ssm82/syntx-ai-mcp/syntx-ai-mcp-usage/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/ssm82/syntx-ai-mcp/syntx-ai-mcp-usage"><img src="https://agentmods.dev/badge/skills/ssm82/syntx-ai-mcp/syntx-ai-mcp-usage.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 101 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 6,651 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	$0.00101	$0.06651
Opus 5.5	$0.00040	$0.02660
Sonnet 5.5	$0.00020	$0.01330
Haiku 4.5	$0.00010	$0.00665

Measured 6d ago against content hash 075c89bbab47, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

syntx-ai-mcp-usage 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 6d 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.

skills/syntx-ai-mcp-usage/SKILL.md · 367 lines

How it starts

The opening of the file, as written. The whole thing — 367 lines — stays where its author put it; the contents beside it link to each section on GitHub.

syntx-ai-mcp Usage

Operational knowledge for driving the syntx-ai-mcp_* MCP tools. This skill captures the non-obvious behaviors discovered through real use that you cannot infer from the tool JSON schemas alone: model identifier conventions, timeout recovery, chat lifecycle, transport-aware security caveats.

When to use this skill

Trigger on any of these conditions:

Calling any syntx-ai-mcp_* tool for the first time in a session.
A prompt exceeds ~1 500 tokens and ask is timing out at the default 60 s.
The user asks to "continue" or "resume" an existing chat.
A model identifier returns 400 — model not found.
Choosing between streaming modes (auto / stream / poll / off).
An authentication failure surfaces and the JWT must be refreshed.
A upload-files or transcribe call returns an unexpected error — transport matters.

Tool inventory — quick reference

The exposed surface is 58 MCP tools (was 49 on 2026-10-13, 51 in 0.2.x — see the v0.3.0 release notes for the full removal list). They cluster into twelve surfaces.

Auth (4)

Tool	Purpose	Blocking?	Notes
`set-token`	Install bearer JWT in-process	yes (fast)	Token lives in memory only; lost on restart. Rejected over HTTP transport.
`whoami`	Identity check, returns `{ authenticated, user }`	yes	Never errors on missing/invalid token — reports `authenticated: false`. Sanitize before logging.
`list-auth-identities`	Linked external identities (`provider`, `email`, `username`, `linked_at`)	yes	Per-provider breakdown that `get-profile` does not carry. Allowlist-projected; anything else upstream adds is dropped at the SDK boundary.
`get-chatwoot-unread`	Support-channel unread state (`{contact_found, has_unread}`)	yes	Server-side gated on `chatwoot_hmac`; the HMAC itself never leaves the server.

Identity (3)

Tool	Purpose	Blocking?	Notes
`get-profile`	Full profile (errors when unauthorized)	yes	Same fields as `whoami` but raises an MCP error when no token is set.
`get-balance`	Token balance for the authenticated user	yes
`get-tokens-history`	Token-spend history (cursor-paginated)	yes	Pass the previous `next_cursor` (if non-null) to walk forward.

Read the full file on GitHub · 367 lines

Files

What ships with it

5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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.

6d ago Changed · +17 lines 075c89bbab47
24d ago Changed · +24 lines ad2794979cfc
1mo ago Changed · -2 lines 0798a6d83781
1mo ago Changed · +13 lines 8c8ba33924b9
2mo ago First seen · 315 lines · 101 tokens per session scan A de8e6bd4a6b4

Subscribe to this mod's changes

syntx-ai-mcp-usage is a skill published in the GitHub repository ssm82/syntx-ai-mcp (11 stars, last pushed 7d ago), licensed MIT. It adds 101 tokens to every session and 6,651 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.

Building agents Data and AI

syntx-ai-mcp-usage next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
syntx-ai-mcp-usagessm82/syntx-ai-mcp	Skill	11	7d ago	MIT	A	101	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