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.
npx skills add ssm82/syntx-ai-mcp --skill syntx-ai-mcp-usagegit clone --depth 1 https://github.com/ssm82/syntx-ai-mcpWrote 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.
[](https://agentmods.dev/skills/ssm82/syntx-ai-mcp/syntx-ai-mcp-usage)<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.
<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>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 | $0.05017 |
| Opus 5 | $0.00051 | $0.02508 |
| Sonnet 5 | $0.00020 | $0.01003 |
| Haiku 4.5 | $0.00010 | $0.00502 |
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 12d 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.
How it starts
The opening of the file, as written. The whole thing — 315 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
askis 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-filesortranscribecall returns an unexpected error — transport matters.
Tool inventory — quick reference
The exposed surface is 28 MCP tools (was 51 in 0.2.x — see the v0.3.0 release notes for the full removal list). They cluster into eight surfaces.
Auth (2)
| 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. |
Identity (2)
| 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 |
Model catalog (3)
| Tool | Purpose | Blocking? | Notes |
|---|---|---|---|
list-ai-services |
List syntx.ai providers | yes | Use to discover ai_name values. |
list-models |
List models with constraints | yes | Source of truth for model_type identifiers. |
get-model-info |
Per-model pricing/limits | yes | Required for cost estimation. |
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.
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.
- 12d ago First seen · 315 lines · 101 tokens per session scan A de8e6bd4a6b4
syntx-ai-mcp-usage is a skill published in the GitHub repository ssm82/syntx-ai-mcp (3 stars, last pushed 1mo ago), licensed MIT. It adds 101 tokens to every session and 5,017 once invoked, about $0.0005 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 2026-08-31.
Other skills, from other repositories
agent-platform-rag-engine-management
Manage and query Agent Platform RAG Engine Corpora and retrieve grounded contexts using the Google GenAI SDK. Use when listing RAG corpora or files, inspecting a corpus, retrieving contexts, or generating content grounded in a RAG corpus. Do not use for standard database queries (use SQL/Spanner skills), Google…
agent-platform-model-registry
Agent Platform Model Registry Management. Use when you need to upload, list, describe, update, or delete machine learning models (and their versions) in the Agent Platform Model Registry. Don't use for model training, model deployment to endpoints, or managing non-Agent Platform models.
foundry-config-setup
Resolve missing setup caused by a hardcoded Foundry project endpoint or model in a sample. Use when a sample fails because it uses a placeholder/hardcoded projectendpoint (for example "https://your-project.services.ai.azure.com") or a hardcoded model instead of reading them from the environment.
google-cloud-solution-agentic-analytics-spark-knowledge-catalog
Discovers requirements and generates guidance to design and deploy a governed, secure agentic-analytics solution for data that's distributed across Google Cloud, other cloud providers, or on-premises. Data that's outside Google Cloud (such as data from Databricks, Snowflake, Salesforce, SAP, or Oracle systems) is…
training-check
Interactively monitor training metrics from the current Codex session, periodically checking WandB or fallback logs for NaN, divergence, plateaus, and broken runs.
nemo-automodel-launcher-config
Configure NeMo AutoModel job launches for interactive runs, Slurm clusters, and SkyPilot cloud execution.