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 startreedata/mcp-pinot --skill pinot-analyticsgit clone --depth 1 https://github.com/startreedata/mcp-pinotWrote 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/startreedata/mcp-pinot/pinot-analytics)<a href="https://agentmods.dev/skills/startreedata/mcp-pinot/pinot-analytics"><img src="https://agentmods.dev/badge/skills/startreedata/mcp-pinot/pinot-analytics/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/startreedata/mcp-pinot/pinot-analytics"><img src="https://agentmods.dev/badge/skills/startreedata/mcp-pinot/pinot-analytics.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 | $0.00051 | $0.00630 |
| Opus 5.5 | $0.00020 | $0.00252 |
| Sonnet 5.5 | $0.00010 | $0.00126 |
| Haiku 4.5 | $0.00005 | $0.00063 |
Grade A, and why
pinot-analytics 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 — 35 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Working with Pinot through the StarTree Pinot tools
Find the data before you query it
- Call
list_tablesto see what exists. Results are paginated; followhas_morewithoffsetwhen the list is long. - Pick candidate tables by name, then call
get_schemafor each. A table's schema name is normally the table name without an_OFFLINEor_REALTIMEsuffix. - Note the time column and the dimensions and metrics you need. Call
get_table_configwhen you need indexing or ingestion details, for example to see whether a column has an index before filtering on it.
Query carefully
read_queryruns one read-onlySELECTorWITH ... SELECT. Anything else is rejected, so don't try to write data with it.- Real-time tables can hold billions of rows. Filter on the time column, aggregate rather than selecting raw rows, and always include a
LIMIT. - Results come back a page at a time, and each page runs the query again. Before you read past the first page, add an
ORDER BYthat makes the order unique, such as the time column plus a key column, or the group-by columns of an aggregation. Without it, pages can overlap or skip rows, especially on a real-time table. Fetch the next page withoffsetonly ifhas_moreis true and the user needs more. - Quote identifiers that clash with SQL keywords using double quotes.
- Summarize what the numbers show, and include the SQL you ran so the user can check it.
When something fails
- For an unknown table or column, re-read the schema and correct the name. Don't retry the same query unchanged.
- For a timeout or connection error, call
test_connectionto see whether the broker or the controller is unreachable, then retry once it passes. - For a permission error, tell the user which call was refused. Their credentials may be read-only on purpose.
Changing schemas, table configs or table filters
create_schema, update_schema, create_table_config and update_table_config change the cluster. reload_table_filters changes only which tables this server exposes, by reloading the filter file named in PINOT_TABLE_FILTER_FILE; it fails when no filter file is configured. All five follow the same steps:
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 · 35 lines · 51 tokens per session scan A ffefa3e57d47
pinot-analytics is a skill published in the GitHub repository startreedata/mcp-pinot (17 stars, last pushed 3d ago), licensed Apache-2.0. It adds 51 tokens to every session and 630 once invoked, about $0.0002 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 2026-10-07.
Other skills, from other repositories
create-pr
Creates a GitHub PR with a Linear-ticket-prefixed title and a decision-led, narrative description for Prisma 8. Use when the user wants to create a pull request, open a PR, or submit changes for review.
schema-exploration
Lists tables, describes columns and data types, identifies foreign key relationships, and maps entity relationships in a database. Use when the user asks about database schema, table structure, column types, what tables exist, ERD, foreign keys, or how entities relate.
atlas-mssql
SQL Server specifics for Atlas (also Azure SQL and MSSQL): login, dev database and URL scope (mode=schema vs mode=database, the database query parameter), compatibility level and collation, system-generated constraint names, clustered index defaults and datetime2 precision in HCL, GO batches and the delimiter…
ha-data-stores
Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…
nornicdb-cypher-queries
Pick fast, predictable Cypher query shapes in NornicDB — point lookups, batch retrieval, pagination, search, traversal, batched UNWIND/MERGE writes, cleanup, multi-tenant isolation. Use when writing or reviewing Cypher whose latency or throughput matters; maps user intent to the executor's hot-path query templates.
volcengine-rds-postgresql
A tool for operating PostgreSQL databases hosted by Volcano Engine's managed database service. PostgreSQL is a relational database used to store structured application data.