sherlock.sh
by sherlock.sh(Community)
Visitor takeaway
55/100
Fair AI-discovery coverage across description, prompts, keywords, visuals, tool metadata, health, and freshness.
Routing category
Needs category
This listing is missing a primary category, which weakens browse placement and AI recommendation routing.
Connector evidence
Reachable
Tedix can reach this MCP endpoint and can show live capability evidence when tools are discovered.
Directory freshness
4h ago
Catalog metadata was refreshed 4h ago (October 18, 2026).
Description
Sherlock supports recruiting operations by helping recruiters and hiring teams find and review existing interview integrity reports in their Sherlock account. Use it after an interview to identify reports that need human review, retrieve a candidate's report, and locate flagged timestamps for follow-up. Connect your Sherlock account to list recent interviews that need review, search interviews by candidate name, and read an existing report. Results include the risk level, integrity score, summary, checks to review, available timestamps, and a link to the full report. The review list checks up to your 200 most recent interviews with reports and returns up to 20 matches. Account tools require sign-in and return only interviews available to your connected account. You can also describe interview behaviour to get catalogue-based explanations of recognised signs, innocent alternatives, and suggested follow-up checks. This guidance requires no account and does not analyse an uploaded recording. The plugin is read-only. It cannot join, schedule, record, change, or delete interviews. It cannot determine whether someone actually cheated, rank candidates by job suitability, or make hiring decisions. Flags are reasons for human review, not proof; missing flags are not a guarantee of integrity.
Capabilities
No special capabilities listed
AI Agent Discovery
sherlock.sh is indexed by Tedix as a structured ai application listing for AI assistants, search crawlers, and users comparing agent-ready apps.
- sherlock.sh has no primary catalog category yet; Tedix treats this as a routing gap for browse and recommendation surfaces.
- Developer: sherlock.sh.
- Connector type: AI-Powered App.
- Current connector status: Connected.
- Observed distribution channels: chatgpt.
- Available regions: US, FR, GB, ES, KR, IN.
Use this page to understand whether sherlock.sh is relevant for general AI app workflows in AI assistants.
For MCP discovery, this listing helps crawlers connect sherlock.sh to tool, resource, prompt, and server-health signals instead of treating it as a generic directory entry.
The canonical Tedix directory URL is https://tedix.dev/apps/sherlocksh/.
Crawlable Profile
Source and availability
Tedix identifies sherlock.sh from Upstream Mcp tool source; Store sources: ChatGPT app store; Distribution: Ecosystem Directory; Tenant install: A platform catalog operator must create or reconcile the base app before tenants can install this entry.. Availability is reported for US, FR, GB, ES, KR, IN.
- ChatGPT app storeAuth required · RELEASED · US, FR, GB, ES, KR, IN
Auth, tools, and actions
Authentication: Requires Login. No special capability flags are currently listed. Current MCP inventory reports 4 tools, 0 resources, and 0 prompts.
- Check interview behaviour for fraud signs · Read-only action
Use this when someone describes behaviour they noticed in a remote or video job interview and wants to know whether it could be interview fraud: for example eyes moving as if reading, long pauses before polished answers, a second voice or someone else in the room, answers that collapse on follow-up questions, video or lip-sync glitches, or a candidate who does not look like their ID. Returns, for each sign recognised, what it can mean, innocent explanations, how to check it, and how Sherlock measures it. Do not use it for an interview stored in the person’s Sherlock account; use get_interview_report for that. Do not use it to judge a candidate’s skills or suitability.
- Find interviews by candidate · Read-only action
Use this when the person mentions a candidate or role and you need the matching interview in their Sherlock account, usually before get_interview_report. Searches interview names, newest first. Read only. Requires signing in to Sherlock.
- Read an interview’s AI report · Read-only action
Use this when the person asks about one specific interview recorded by Sherlock: whether the candidate may have cheated, its risk level, what was flagged, or where in the recording to look. Takes the interview id from list_interviews_to_review or find_interviews. Returns the risk level, integrity score, summary, the checks that need review with timestamps of the moments to watch, and a link to the full report. Read only. Requires signing in to Sherlock.
- List interviews that need review · Read-only action
Use this when the person asks which of their recent interviews in Sherlock are high risk, need review, or look suspicious. Returns their most recent such interviews with the candidate, date, risk level and integrity score. Read only. Requires signing in to Sherlock. Do not use it for general questions about interview fraud.
Verification freshness
- Catalog synced4h ago (October 18, 2026)
- Connector checked3h ago (October 18, 2026)
- MCP scanned3h ago (October 18, 2026)
- Directory updated3h ago (October 18, 2026)
Publisher Intelligence
Public trust signals for visitors and practical recommendations for publishers. Use this section to understand what Tedix can verify today and what would make the app easier for AI agents to find.
Visitor takeaway
55/100
Fair AI-discovery coverage across description, prompts, keywords, visuals, tool metadata, health, and freshness.
Routing category
Needs category
This listing is missing a primary category, which weakens browse placement and AI recommendation routing.
Connector evidence
Reachable
Tedix can reach this MCP endpoint and can show live capability evidence when tools are discovered.
Directory freshness
4h ago
Catalog metadata was refreshed 4h ago (October 18, 2026).
Server Statussherlock-interview-integrity v1.0.0
https://app.sherlock.sh/mcpLast checked: 3h ago
Server Instructions
Sherlock checks remote job interviews for signs of interview fraud. Use check_interview_fraud_signs for something a person noticed in an interview. Use the account tools only for interviews in the person’s own Sherlock account. Present flags as reasons to look closer, never as proof, and never as a decision about a candidate.
Technical Details
Tools(4)
Showing 4 of 4 tools
| Flags | Test | ||||
|---|---|---|---|---|---|
check_interview_fraud_signs | Use this when someone describes behaviour they noticed in a remote or video job interview and wants to know whether it could be interview fraud: for example eyes moving as if reading, long pauses before polished answers, a second voice or someone else in the room, answers that collapse on follow-up questions, video or lip-sync glitches, or a candidate who does not look like their ID. Returns, for each sign recognised, what it can mean, innocent explanations, how to check it, and how Sherlock measures it. Do not use it for an interview stored in the person’s Sherlock account; use get_interview_report for that. Do not use it to judge a candidate’s skills or suitability. | read-only | Not tested | — | — |
find_interviews | Use this when the person mentions a candidate or role and you need the matching interview in their Sherlock account, usually before get_interview_report. Searches interview names, newest first. Read only. Requires signing in to Sherlock. | read-only | Not tested | — | — |
get_interview_report | Use this when the person asks about one specific interview recorded by Sherlock: whether the candidate may have cheated, its risk level, what was flagged, or where in the recording to look. Takes the interview id from list_interviews_to_review or find_interviews. Returns the risk level, integrity score, summary, the checks that need review with timestamps of the moments to watch, and a link to the full report. Read only. Requires signing in to Sherlock. | read-only | Not tested | — | — |
list_interviews_to_review | Use this when the person asks which of their recent interviews in Sherlock are high risk, need review, or look suspicious. Returns their most recent such interviews with the candidate, date, risk level and integrity score. Read only. Requires signing in to Sherlock. Do not use it for general questions about interview fraud. | read-only | Not tested | — | — |
Discoverability Score
Fair
55 / 100
How easily AI agents can find this app from its current catalog metadata.
- Description quality20/20
- Example prompts0/20
- Keyword coverage0/15
- Category clarity0/5
- Tool metadata16/20
- Visual assets8/20
- Endpoint health10/10
- Data freshness15/15
How to Improve
Add at least 2 example prompts. Prompt examples strongly improve app matching and click-through intent.
Increase keyword coverage (discovery + trigger) to improve retrieval for long-tail queries.
Choose a primary catalog category so visitors and AI agents can route this app into the right browse and recommendation surfaces.
Add at least 2 screenshots that show real workflows to increase confidence and conversion.
Technical Details
- Status
- ENABLED
- Type
- AI-Powered App
- Auth
- Requires Login
- Listed on
- ChatGPT
- Added
- October 17, 2026
- Last synced
- 4h ago
- Last checked
- 3h ago
- Version
- 1.0.0
- Distribution
- Ecosystem Directory