ATR: Automation for Token Reduction
PYPI · ATR-MCP
MCP proxy that hides tool lists and shrinks tool results so your AI uses fewer tokens.
Available components
Last scanned (2 hours ago)
Scores higher than 67% of PyPI servers
Category Developer Tools
How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score → Why this is hard to score →
Supply Chain Security100
- No malware found by supply-chain analysis.Pass
- No known CVEs affecting this package version or its production dependencies.Pass
- Runs setuptools.build_meta at install time, a recognised build step with no custom scripting around it. View diagnostics → Pass
- No production dependencies, so there is no dependency health to assess. View diagnostics → Pass
Provenance & Transparency45
- Source repository is publicly reachable at the declared URL. View diagnostics → Pass
- Provenance check failed: no build-provenance attestation is published. See how to fix → View diagnostics → Fail
- Clear OSI-approved license (MIT).Pass
- Actively maintained (last published 7 days ago).Pass
- Disclosure check failed: no security disclosure policy was found in the source repository. See how to fix → Fail
Schema Quality & AI Usability63
- AI-judged instruction clarity (good).Pass
- Tool/resource definitions use about 1037 tokens (~103/item across 10 items; 10 tools + 0 resources), lean.Pass
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management27
- Stability observed for 8 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage85
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 54% of tool parameters carry a description.Partial
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- We read all 10 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
- An AI judge read all 11 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
- Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.
- 5 Nov 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 23 to 27. That category is still filling its 30-day observation window: 7 days of observed history at the previous scan, 8 at this one. The score rises as the window fills, whether or not the server changes.
- 2 Nov 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 13 to 17. That category is still filling its 30-day observation window: 4 days of observed history at the previous scan, 5 at this one. The score rises as the window fills, whether or not the server changes.
- 31 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 7 to 10. That category is still filling its 30-day observation window: 2 days of observed history at the previous scan, 3 at this one. The score rises as the window fills, whether or not the server changes.
- 29 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 0 to 3. That category is still filling its 30-day observation window: 0 days of observed history at the previous scan, 1 at this one. The score rises as the window fills, whether or not the server changes.
- 28 Oct 26 67
First indexed and scored.
Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.
Captured 5 Nov 2026 · Analysed pypi/atr-mcp@1.0.0
Provenance No attestation
The registry publishes no build provenance for this version, so there is nothing to verify.
| Result | No attestation |
|---|---|
| Ecosystem | pypi |
| Reason | No attestation published |
Background: How many MCP packages publish verified provenance →
Install scripts 1 script
| Hook | Tier | Command |
|---|---|---|
| build_backend | allowlisted | setuptools.build_meta |
Background: Why install scripts are a supply-chain risk →
Dependencies 0 packages
| Packages resolved | 0 |
|---|---|
| Tree resolution | Complete |
Background: SBOMs and build attestations, explained →
The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →
atr_call ~56
Run a tool that changes something ([w] in atr_find_tools). Result is compressed.
| Name | Type | Req | Description |
|---|---|---|---|
| arguments | object | – | – |
| budget | integer | – | Max tokens for the result (default from config). |
| tool | string | yes | – |
No output schema declared.
No examples provided.
atr_diff ~119
What changed, compactly: git diff with 1 line of context, lockfiles/generated/binary files listed but not shown. Default: uncommitted changes. Use instead of `git diff`.
| Name | Type | Req | Description |
|---|---|---|---|
| budget | integer | – | – |
| file | string | – | Only this file (path from the repo root). |
| path | string | – | Folder inside the repo (default: the project). |
| ref | string | – | Compare with this commit/branch, e.g. main or HEAD~1. |
| staged | boolean | – | Only staged changes. |
No output schema declared.
No examples provided.
atr_find_tools ~69
Find tools on the connected servers for a task. Returns compact signatures (* = required).
| Name | Type | Req | Description |
|---|---|---|---|
| detail | boolean | – | Also return the parameter schemas. |
| k | integer | – | How many tools (default 5). |
| query | string | yes | What you want to do, in a few words. |
No output schema declared.
No examples provided.
atr_query ~124
Read part of a stashed result by ref. Data: path/where/fields/group_by. Text: search (regex).
| Name | Type | Req | Description |
|---|---|---|---|
| fields | array | – | – |
| group_by | string | – | – |
| limit | integer | – | – |
| offset | integer | – | – |
| path | string | – | Dotted path, e.g. data.items or items.*.user |
| ref | string | yes | – |
| search | string | – | – |
| where | array | – | Filters: key=v, key!=v, key>n, key<n, key~regex |
No output schema declared.
No examples provided.
atr_read ~61
Run a read-only tool ([r] in atr_find_tools). Result is compressed; big ones are stashed.
| Name | Type | Req | Description |
|---|---|---|---|
| arguments | object | – | – |
| budget | integer | – | Max tokens for the result (default from config). |
| tool | string | yes | – |
No output schema declared.
No examples provided.
atr_read_file ~135
Read part of a local file. Pass lines= (e.g. from a search hit) or search= to get only what you need; with just a path, big code files return an outline instead of the whole file.
| Name | Type | Req | Description |
|---|---|---|---|
| budget | integer | – | – |
| context | integer | – | Lines around each search match (default 0). |
| fresh | boolean | – | Send the full text even if you read it before. |
| lines | string | – | Line range, e.g. 120-180. |
| path | string | yes | – |
| search | string | – | Regex: only matching lines, with line numbers. |
No output schema declared.
No examples provided.
atr_repo_map ~48
Project layout with each code file's top-level functions/classes. Start here in a codebase.
| Name | Type | Req | Description |
|---|---|---|---|
| budget | integer | – | – |
| path | string | – | Folder (default: the project). |
No output schema declared.
No examples provided.
atr_run ~69
Run a shell command (tests, build, lint) and get compressed output: failures kept, noise cut.
| Name | Type | Req | Description |
|---|---|---|---|
| budget | integer | – | – |
| command | string | yes | – |
| cwd | string | – | Folder (default: the project). |
| timeout | integer | – | Seconds (default 300). |
No output schema declared.
No examples provided.
atr_search_code ~117
Find where something is defined or used, before reading any file. Regex, grouped by file (path:line: text); context=3 shows the lines around each hit, often enough to answer.
| Name | Type | Req | Description |
|---|---|---|---|
| budget | integer | – | – |
| context | integer | – | Lines to show around each match (default 0, try 3). |
| glob | string | – | Only these files, e.g. *.py or src/**/*.ts |
| path | string | – | Folder (default: the project). |
| pattern | string | yes | – |
No output schema declared.
No examples provided.
atr_stats ~16
Tokens ATR has saved in this session.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
How do I install the ATR: Automation for Token Reduction MCP server?
ATR: Automation for Token Reduction runs locally as a PyPI package, launched with uvx atr-mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
pypi · atr-mcp
claude mcp add jacobbhatt12-atr -- uvx atr-mcp
What is the ATR: Automation for Token Reduction MCP server?
ATR: Automation for Token Reduction is an MCP server listed in the public MCP registry as io.github.JacobBhatt12/atr. MCP proxy that hides tool lists and shrinks tool results so your AI uses fewer tokens. This page covers its PyPI package (atr-mcp).
Is the ATR: Automation for Token Reduction MCP server safe to use?
ATR: Automation for Token Reduction scores 71 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 5 November 2026. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.
What tools does the ATR: Automation for Token Reduction MCP server expose?
ATR: Automation for Token Reduction exposes 10 tools: atr_find_tools, atr_read, atr_call, atr_query, atr_read_file, and 5 more. Their descriptions and schemas cost roughly 814 tokens of context every time the server is loaded.
Is the ATR: Automation for Token Reduction MCP server still maintained?
ATR: Automation for Token Reduction is still listed as active in the MCP registry. We last reached this channel on 5 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.
What licence is the ATR: Automation for Token Reduction MCP server under?
ATR: Automation for Token Reduction declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.