TweekIT MCP Server
PYPI · TWEEKIT · 2 COMPONENTS
Preflight and convert 450+ file types for AI workflows via TweekIT MCP & SDK (Equilibrium).
Available components
Last scanned (9 hours ago)
Scores higher than 56% of PyPI servers
Category Documents and Files
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 Security50
- Malware scan not yet available for this package.Unverified
- 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
- 1 of 26 dependencies flagged as unhealthy. View diagnostics → Partial
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
- Security-disclosure policy not yet verified: we couldn't inspect the source repository.Unverified
Schema Quality & AI Usability79
- 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).Pass
- AI-judged instruction clarity (good).Pass
- Context-footprint check failed: tool/resource definitions use about 1619 tokens (~161/item across 10 items; 8 tools + 2 resources), over budget; trim descriptions and params. See how to fix → Fail
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management0
- Stability not yet verified: not enough scan history yet (needs a 30-day window).Unverified
Tool Coverage100
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 100% of tool parameters carry a description.Pass
- Structured output schemas are declared (50% of tools); any adoption earns full credit.Pass
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- All 1 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation.Pass
- An AI judge read all 9 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
- Implements a current MCP spec version (2026-07-28).Pass
Unverified: 1 category
A category scored 0 because we could not verify it: a data source with nothing on this package, evidence we could not reach, or a check we could not run. We only credit what we can confirm.
Checks we ran (13)
- Known CVEs
- Install scripts
- Dependency health
- Source repository
- Provenance
- License
- Maintenance
- Schema quality
- Tool coverage
- Injection markers
- Destructive annotations
- Judged manipulation
- MCP protocol
Checks we could not complete (3)
These are gaps on our side, not findings about this package. We only credit what we can confirm, so a category made up entirely of them scores 0.
- Malware scan in Supply Chain SecurityMalware scan not yet available for this package.
- Security disclosure in Provenance & TransparencySecurity-disclosure policy not yet verified: we couldn't inspect the source repository.
- Stability in Stability & Change Management (scores 0 for this)Stability not yet verified: not enough scan history yet (needs a 30-day window).
Does not apply to this package (2)
- Endpoint SecurityScored on hosted endpoints only. A package has no live endpoint of its own for us to probe.
- Transport & ReachabilityScored on hosted endpoints only. A package has no live endpoint of its own for us to probe.
The score does not measure everything. What the score does not measure →
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 −15
- Malware scan: pass → unverified ▼ security
- Security disclosure: fail → unverified ▼ functional
- 3 Nov 26 +15
- Malware scan: unverified → pass ▲ security
- 2 Nov 26 −15
- Malware scan: pass → unverified ▼ security
- 29 Oct 26 +15
- Malware scan: unverified → pass ▲ security
- 28 Oct 26 56
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/tweekit@1.8.0
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 | Known build tool | setuptools.build_meta |
Background: Why install scripts are a supply-chain risk →
Dependencies 26 packages
| Packages resolved | 26 |
|---|---|
| Stale | 1 |
| 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 →
convert Convert Base64 Document ~327
Convert an uploaded document payload with TweekIT. The file must already be base64 encoded (see `blob`). The conversion can be resized and cropped by providing optional geometry parameters. For raster outputs, set `alpha`/`bgColor` to control transparency handling.
| Name | Type | Req | Description |
|---|---|---|---|
| alpha | boolean | – | Preserve alpha transparency when producing raster formats. |
| apiKey | – | – | TweekIT API key passed via the ApiKey header. Defaults to the TWEEKIT_API_KEY environment variable when omitted. |
| apiSecret | – | – | TweekIT API secret paired with the apiKey. Defaults to the TWEEKIT_API_SECRET environment variable when omitted. |
| bgColor | string | – | Background color (hex RGB) to composite behind transparent pixels. |
| blob | string | yes | Base64 encoded document payload (DocData). |
| height | integer | – | Optional pixel height for the converted output. |
| inext | string | yes | Input file extension (e.g., pdf, docx, png). |
| noRasterize | boolean | – | Forward to TweekIT to disable rasterization when supported. |
| outfmt | string | yes | Requested output format to send as Fmt. |
| page | integer | – | Page number to convert for multi-page inputs. |
| width | integer | – | Optional pixel width for the converted output. |
| x1 | integer | – | Left crop coordinate in source pixels. |
| x2 | integer | – | Right crop coordinate in source pixels. |
| y1 | integer | – | Top crop coordinate in source pixels. |
| y2 | integer | – | Bottom crop coordinate in source pixels. |
No output schema declared.
No examples provided.
convert_file Convert Local File ~369
Convert a local file on disk with TweekIT without base64-encoding into the LLM prompt context. When `output_path` is provided and conversion returns binary media (`Image` or `File`), the converted bytes are written directly to `output_path` and a compact JSON receipt is returned. Otherwise, returns a FastMCP `Image` or `File` payload directly.
| Name | Type | Req | Description |
|---|---|---|---|
| alpha | boolean | – | Preserve alpha transparency when producing raster formats. |
| apiKey | – | – | TweekIT API key passed via the ApiKey header. Defaults to TWEEKIT_API_KEY when omitted. |
| apiSecret | – | – | TweekIT API secret paired with the apiKey. Defaults to TWEEKIT_API_SECRET when omitted. |
| bgColor | string | – | Background color (hex RGB) to composite behind transparent pixels. |
| file_path | string | yes | Local filesystem path to the input document or image. |
| height | integer | – | Optional pixel height for the converted output. |
| inext | – | – | Override for the input file extension (inferred from file_path when omitted). |
| noRasterize | boolean | – | Forward to TweekIT to disable rasterization when supported. |
| outfmt | string | yes | Requested output format (e.g., pdf, png, webp, txt). |
| output_path | – | – | Optional local filesystem path to write the converted output directly to disk. |
| page | integer | – | Page number to convert for multi-page inputs. |
| width | integer | – | Optional pixel width for the converted output. |
| x1 | integer | – | Left crop coordinate in source pixels. |
| x2 | integer | – | Right crop coordinate in source pixels. |
| y1 | integer | – | Top crop coordinate in source pixels. |
| y2 | integer | – | Bottom crop coordinate in source pixels. |
No output schema declared.
No examples provided.
convert_url Convert Remote URL Document ~339
Download a remote file and convert it with TweekIT in one step. This helper first fetches `url`, infers the input extension when possible, and then forwards the bytes to `convert`. Supply `fetchHeaders` when the remote resource needs authentication or custom headers.
| Name | Type | Req | Description |
|---|---|---|---|
| alpha | boolean | – | Preserve alpha transparency when producing raster formats. |
| apiKey | – | – | TweekIT API key passed via the ApiKey header. Defaults to the TWEEKIT_API_KEY environment variable when omitted. |
| apiSecret | – | – | TweekIT API secret paired with the apiKey. Defaults to the TWEEKIT_API_SECRET environment variable when omitted. |
| bgColor | string | – | Background color (hex RGB) to composite behind transparent pixels. |
| fetchHeaders | – | – | Optional HTTP headers to include when downloading the URL. |
| height | integer | – | Optional pixel height for the converted output. |
| inext | – | – | Override for the detected input extension (e.g., pdf). |
| noRasterize | boolean | – | Forward to TweekIT to disable rasterization when supported. |
| outfmt | string | yes | Requested output format to send as Fmt. |
| page | integer | – | Page number to convert for multi-page inputs. |
| url | string | yes | Direct download URL for the source document or image. |
| width | integer | – | Optional pixel width for the converted output. |
| x1 | integer | – | Left crop coordinate in source pixels. |
| x2 | integer | – | Right crop coordinate in source pixels. |
| y1 | integer | – | Top crop coordinate in source pixels. |
| y2 | integer | – | Bottom crop coordinate in source pixels. |
No output schema declared.
No examples provided.
delete_document Delete Uploaded Document ~157
Immediately delete a document and all associated files by DocId. Use this when an AI workflow needs to explicitly clean up an uploaded document before its 20-minute auto-expiry — for example, when a user cancels mid-workflow. This is only needed when using the REST API upload flow directly; the MCP convert tools handle their own cleanup automatically.
| Name | Type | Req | Description |
|---|---|---|---|
| apiKey | – | – | TweekIT API key passed via the ApiKey header. Defaults to the TWEEKIT_API_KEY environment variable when omitted. |
| apiSecret | – | – | TweekIT API secret paired with the apiKey. Defaults to the TWEEKIT_API_SECRET environment variable when omitted. |
| docId | string | yes | The DocId returned from a prior upload to delete. |
Structured output declared, but exposes no named fields.
No examples provided.
doctype Inspect Supported Document Types ~103
Retrieve a list of supported file formats or map a file extension to its document type.
| Name | Type | Req | Description |
|---|---|---|---|
| apiKey | – | – | TweekIT API key passed via the ApiKey header. Defaults to the TWEEKIT_API_KEY environment variable when omitted. |
| apiSecret | – | – | TweekIT API secret paired with the apiKey. Defaults to the TWEEKIT_API_SECRET environment variable when omitted. |
| extension | string | – | File extension to inspect; use '*' to list all supported inputs. |
Structured output declared, but exposes no named fields.
No examples provided.
fetch Fetch & Normalize URL ~61
Fetch a URL and return content. - Images return as FastMCP Image. - PDFs return as File(format="pdf"). - Text/JSON return as a JSON payload with metadata and text.
| Name | Type | Req | Description |
|---|---|---|---|
| url | string | yes | HTTP or HTTPS URL to retrieve and normalize. |
No output schema declared.
No examples provided.
preflight AI Hub Preflight & Format Recommendation ~165
Validate whether a file format is supported by TweekIT and recommend the optimal AI-ready output format. Designed for AI Hub preflight checks (such as Maitrix AI Hub, Claude, OpenAI, and Gemini pipelines) to determine whether an incoming file needs TweekIT normalization and which output format (`pdf`, `png`, `webp`, `txt`) and parameters to use.
| Name | Type | Req | Description |
|---|---|---|---|
| filename_or_ext | string | yes | Input filename, path, or extension to validate (e.g., 'scan.psd', 'report.xls', 'dwg'). |
| target_provider | string | – | Target AI provider/hub profile ('claude', 'openai', 'gemini', 'mistral', 'grok', 'deepseek', 'openrouter', or 'default'). |
Structured output declared, but exposes no named fields.
No examples provided.
search Web Search (DuckDuckGo) ~69
Simple web search using DuckDuckGo HTML endpoint. Returns a list of {title, url, snippet} objects. Best‑effort parsing.
| Name | Type | Req | Description |
|---|---|---|---|
| max_results | integer | – | Maximum number of results to return (1-10). |
| query | string | yes | Search keywords to send to DuckDuckGo. |
Structured output declared, but exposes no named fields.
No examples provided.
How do I install the TweekIT MCP Server server?
TweekIT MCP Server runs locally as a PyPI package, launched with uvx tweekit --transport stdio. Ready-made configuration for Claude, Cursor, VS Code, Codex and 3 more is on this page, copied from each client's own documentation.
pypi · tweekit
claude mcp add equilibrium-team-tweekit -- uvx tweekit --transport stdio
What is the TweekIT MCP Server server?
TweekIT MCP Server is listed in the public MCP registry as io.github.equilibrium-team/tweekit. Preflight and convert 450+ file types for AI workflows via TweekIT MCP & SDK (Equilibrium). This page covers its PyPI package (tweekit).
Is the TweekIT MCP Server server safe to use?
TweekIT MCP Server scores 56 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 TweekIT MCP Server server expose?
TweekIT MCP Server exposes 8 tools: doctype, preflight, convert, convert_url, convert_file, and 3 more. Their descriptions and schemas cost roughly 1,590 tokens of context every time the server is loaded.
Is the TweekIT MCP Server server still maintained?
TweekIT MCP Server 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 TweekIT MCP Server server under?
TweekIT MCP Server declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.
What did VerifyMCP test on the TweekIT MCP Server server?
VerifyMCP ran 13 checks on TweekIT MCP Server, covering Known CVEs, Install scripts, Dependency health, Source repository and 9 more. 3 items could not be completed, a gap on our side rather than a finding about TweekIT MCP Server: Malware scan, Security disclosure and Stability. One category scores 0 for that reason, because we only credit what we can confirm. Endpoint Security and Transport & Reachability do not apply to a PyPI package, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.