jevreel
PYPI · JEVREEL
Search and understand videos without embeddings: contact sheets plus Jev typed decisions.
Available components
Last scanned (9 hours ago)
Scores higher than 67% of PyPI servers
Category Design and Media
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 Security49
- Malware scan not yet available for this package.Unverified
- No known CVEs affecting this package version or its production dependencies.Pass
- Runs uv_build at install time, a recognised build step with no custom scripting around it. View diagnostics → Pass
- 4 of 31 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency100
- Source repository is publicly reachable at the declared URL. View diagnostics → Pass
- Cryptographically verified build provenance (signed, bound to DeepAleph/jevreel). View diagnostics → Pass
- Clear OSI-approved license (MIT).Pass
- Actively maintained (last published 5 days ago).Pass
- Publishes a security disclosure policy (SECURITY.md).Pass
Schema Quality & AI Usability65
- AI-judged instruction clarity (good).Pass
- Context-footprint check failed: tool/resource definitions use about 1376 tokens (~137/item across 10 items; 10 tools + 0 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 Management20
- Stability observed for 6 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage94
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 82% 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 current MCP spec version (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.
- 23 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 17 to 20. That category is still filling its 30-day observation window: 5 days of observed history at the previous scan, 6 at this one. The score rises as the window fills, whether or not the server changes.
- 21 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 10 to 13. That category is still filling its 30-day observation window: 3 days of observed history at the previous scan, 4 at this one. The score rises as the window fills, whether or not the server changes.
- 19 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 3 to 7. That category is still filling its 30-day observation window: 1 days of observed history at the previous scan, 2 at this one. The score rises as the window fills, whether or not the server changes.
- 18 Oct 26 0
- Stability: unverified → 0.03 ▲ functional
- 17 Oct 26 64
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 23 Oct 2026 · Analysed pypi/jevreel@0.2.0
Provenance Verified
A signed build attestation was found and verified, binding this exact artifact to the source repository it claims to come from.
| Result | Verified |
|---|---|
| Ecosystem | pypi |
| Reason | Verified |
| Discovered via | Registry attestation endpoint |
| Source repo | DeepAleph/jevreel |
| Certificate issuer | https://token.actions.githubusercontent.com |
| Certificate SAN | https://github.com/DeepAleph/jevreel/.github/workflows/release.yml@refs/tags/v0.2.0 |
| Rekor log index | 3294235292 |
| Predicate type | PyPI publish attestation https://docs.pypi.org/attestations/publish/v1 |
| Subject digest | sha256:e33c85ae7f273805c2b5d36c0021baf1b659c80db804ed797b902f6b5a6845b5 |
Background: How many MCP packages publish verified provenance →
Install scripts 1 script
| Hook | Tier | Command |
|---|---|---|
| build_backend | allowlisted | uv_build |
Background: Why install scripts are a supply-chain risk →
Dependencies 31 packages
| Packages resolved | 31 |
|---|---|
| Stale | 3 |
| No linked repository | 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 →
ask_video Ask Video ~191
Find the moments in a video that match a description. Jev screens every contact sheet in parallel, re-checks the top-ranked windows on full frames, and returns times, probabilities and nearby speech.
| Name | Type | Req | Description |
|---|---|---|---|
| end | – | – | Only search up to this second. |
| limit | integer | – | Most hits to return. |
| mode | string | – | visual: on screen only. speech: transcript only. both: either. auto: both when there is a transcript. |
| query | string | yes | What to find, e.g. 'a whiteboard diagram' or 'the speaker mentions pricing'. |
| start | – | – | Only search from this second. |
| thumbnails | integer | – | How many top hits to show as images. |
| verify | boolean | – | Re-check the top-ranked windows on full frames (recommended). |
| video | string | yes | Video ID from index_video, or the file path or URL that was indexed. |
No output schema declared.
No examples provided.
ask_whole_video Ask Whole Video ~120
One typed answer about the whole video, from a single request that sees a storyboard of the video, the per-minute timeline and the full transcript.
| Name | Type | Req | Description |
|---|---|---|---|
| kind | string | – | noul: yes/no probability. choice: pick one option. score: rate on ordered levels. |
| options | – | – | Options for choice, or levels lowest first for score (at most 10). |
| question | string | yes | A question about the entire video. |
| video | string | yes | Video ID from index_video, or the file path or URL that was indexed. |
No output schema declared.
No examples provided.
find_in_video Find In Video ~150
Find every moment the subject of a reference photo appears, without embeddings: Jev compares the photo with every contact sheet, then re-checks the best windows on full frames.
| Name | Type | Req | Description |
|---|---|---|---|
| end | – | – | – |
| image_path | string | yes | Local path to a reference photo of the person, logo or object. |
| limit | integer | – | – |
| note | – | – | What the reference shows, e.g. 'person', 'logo', 'red backpack'. |
| start | – | – | – |
| thumbnails | integer | – | – |
| verify | boolean | – | Re-check the top-ranked windows on full frames. |
| video | string | yes | Video ID from index_video, or the file path or URL that was indexed. |
No output schema declared.
No examples provided.
index_video Index Video ~122
Prepare a video: contact sheets at 1 frame per second, the transcript (captions, or local speech-to-text if installed), and a timeline of default answers for every minute. Run once per video; later calls return the cached index immediately and only run lenses it has not seen.
| Name | Type | Req | Description |
|---|---|---|---|
| force | boolean | – | Re-index even if this video was indexed before. |
| lenses | – | – | Your own questions to ask of every minute while indexing, at almost no extra cost. |
| source | string | yes | Path to a local video file, or a video URL. |
No output schema declared.
No examples provided.
list_videos List Videos ~16
Videos already indexed on this machine.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
locate_in_frame Locate In Frame ~111
Box a target in the full-resolution frame at a given second and return the crop, for reading small text or checking details. Says found=false when the target is not in that frame.
| Name | Type | Req | Description |
|---|---|---|---|
| at | number | yes | Seconds from the start of the video. |
| image_path | – | – | Reference photo of what to locate. |
| target | – | – | What to locate, e.g. 'the code editor'. |
| video | string | yes | Video ID from index_video, or the file path or URL that was indexed. |
No output schema declared.
No examples provided.
query_timeline Query Timeline ~96
Filter a video's per-minute timeline (default answers plus every lens) with no requests and no cost.
| Name | Type | Req | Description |
|---|---|---|---|
| video | string | yes | Video ID from index_video, or the file path or URL that was indexed. |
| where | – | – | Conditions joined by 'and', e.g. 'people > 0.8 and setting == outdoors' or 'safety.helmet_off >= 0.7'. Omit to get every minute. |
No output schema declared.
No examples provided.
run_lens Run Lens ~101
Ask your own typed questions of every minute of an indexed video and keep the answers as timeline columns. Questions: noul (yes/no; also finds the second it happens), choice (options), or score (levels, lowest first). One request per minute; filter the results afterwards with query_timeline.
| Name | Type | Req | Description |
|---|---|---|---|
| lens | object | yes | – |
| video | string | yes | Video ID from index_video, or the file path or URL that was indexed. |
No output schema declared.
No examples provided.
video_transcript Video Transcript ~59
What is said between two times (the whole video when both are omitted), with timestamps.
| Name | Type | Req | Description |
|---|---|---|---|
| end | – | – | – |
| start | – | – | – |
| video | string | yes | Video ID from index_video, or the file path or URL that was indexed. |
No output schema declared.
No examples provided.
zoom_video Zoom Video ~100
Full-resolution frames between two times, for you to look at directly.
| Name | Type | Req | Description |
|---|---|---|---|
| count | integer | – | Number of evenly spaced frames. |
| end | number | yes | Seconds from the start of the video. |
| max_side | integer | – | Longest side of each frame in pixels. |
| start | number | yes | Seconds from the start of the video. |
| video | string | yes | Video ID from index_video, or the file path or URL that was indexed. |
No output schema declared.
No examples provided.
How do I install the jevreel MCP server?
jevreel runs locally as a PyPI package, launched with uvx jevreel. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
pypi · jevreel
claude mcp add deepaleph-jevreel -- uvx jevreel
What is the jevreel MCP server?
jevreel is an MCP server listed in the public MCP registry as io.github.DeepAleph/jevreel. Search and understand videos without embeddings: contact sheets plus Jev typed decisions. This page covers its PyPI package (jevreel).
Is the jevreel MCP server safe to use?
jevreel scores 67 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 23 October 2026. Its build provenance is signed and verified. 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 jevreel MCP server expose?
jevreel exposes 10 tools: index_video, ask_video, find_in_video, locate_in_frame, zoom_video, and 5 more. Their descriptions and schemas cost roughly 1,066 tokens of context every time the server is loaded.
Is the jevreel MCP server still maintained?
jevreel is still listed as active in the MCP registry. We last reached this channel on 23 October 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 jevreel MCP server under?
jevreel declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.