AI Workbench MCP
PYPI · AI-WORKBENCH-MCP · SCANNED SEP 21
Goose-first MCP server for Workbench-owned acceptance evidence, validation gates, and analytics.
Available components
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 native-build step with no shell scripting around it. View diagnostics → Pass
- 0 of 29 dependencies flagged as unhealthy. View diagnostics → Pass
Provenance & Transparency32
- 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
- License check failed: no license is declared. See how to fix → Fail
- Actively maintained (last published 124 days ago).Pass
- Disclosure check failed: no security disclosure policy was found in the source repository. See how to fix → Fail
Schema Quality & AI Usability51
- AI-judged instruction clarity (fair).Partial
- Tool/resource definitions use about 561 tokens (~80/item across 7 items; 7 tools + 0 resources), lean.Pass
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management87
- Stability observed for 26 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage71
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 0% of tool parameters carry a description.Fail
- Structured output schemas are declared (100% 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
- We read all 7 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
- An AI judge read all 7 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
How do I install the AI Workbench MCP server?
AI Workbench MCP runs locally as a PyPI package, launched with uvx ai-workbench-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 · ai-workbench-mcp
claude mcp add hrishikesh-thakre-ai-workbench-mcp -- uvx ai-workbench-mcp
{
"mcpServers": {
"hrishikesh-thakre-ai-workbench-mcp": {
"command": "uvx",
"args": [
"ai-workbench-mcp"
]
}
}
} {
"servers": {
"hrishikesh-thakre-ai-workbench-mcp": {
"command": "uvx",
"args": [
"ai-workbench-mcp"
]
}
}
} codex mcp add hrishikesh-thakre-ai-workbench-mcp -- uvx ai-workbench-mcp
{
"$schema": "https://opencode.ai/config.json",
"mcp": {
"hrishikesh-thakre-ai-workbench-mcp": {
"type": "local",
"command": [
"uvx",
"ai-workbench-mcp"
],
"enabled": true
}
}
} openclaw mcp add hrishikesh-thakre-ai-workbench-mcp --command uvx --arg ai-workbench-mcp
mcp_servers:
hrishikesh-thakre-ai-workbench-mcp:
command: "uvx"
args: ["ai-workbench-mcp"] {
"McpServers": {
"hrishikesh-thakre-ai-workbench-mcp": {
"Transport": "stdio",
"Command": "uvx",
"Arguments": [
"ai-workbench-mcp"
]
}
}
} assistant mcp add hrishikesh-thakre-ai-workbench-mcp -t stdio -c uvx -a ai-workbench-mcp
{
"mcpServers": {
"hrishikesh-thakre-ai-workbench-mcp": {
"command": "uvx",
"args": [
"ai-workbench-mcp"
]
}
}
} 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.
- 20 Sept 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 80 to 83. That category is still filling its 30-day observation window: 24 days of observed history at the previous scan, 25 at this one. The score rises as the window fills, whether or not the server changes.
- 19 Sept 26 −3
- Stability: pass → 0.80 functional
- 18 Sept 26 0
- Stability: 0.97 → pass security
- 17 Sept 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 93 to 97. That category is still filling its 30-day observation window: 28 days of observed history at the previous scan, 29 at this one. The score rises as the window fills, whether or not the server changes.
- 15 Sept 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 87 to 90. That category is still filling its 30-day observation window: 26 days of observed history at the previous scan, 27 at this one. The score rises as the window fills, whether or not the server changes.
- 13 Sept 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 80 to 83. That category is still filling its 30-day observation window: 24 days of observed history at the previous scan, 25 at this one. The score rises as the window fills, whether or not the server changes.
- 12 Sept 26 −3
- Stability: pass → 0.80 functional
- 11 Sept 26 0
- Stability: 0.97 → pass security
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 21 Sept 2026 · Analysed pypi/ai-workbench-mcp@0.6.0a0
Provenance No attestation
The registry publishes no build provenance for this version, so there is nothing to verify.
| Result | No attestation |
|---|---|
| Ecosystem | pypi |
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 29 packages
| Packages resolved | 29 |
|---|---|
| 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 →
workbench_analyze_runs ~65
Analyze local Workbench run ledgers and write report artifacts.
| Name | Type | Req | Description |
|---|---|---|---|
| evals_dir | string | – | – |
| evidence_scope | string | – | – |
| out_dir | – | – | – |
| runs_dir | string | – | – |
| since | – | – | – |
| task_type | – | – | – |
Structured output declared, but exposes no named fields.
No examples provided.
workbench_open_run ~115
Create a Workbench run folder and initial evidence artifacts.
| Name | Type | Req | Description |
|---|---|---|---|
| auto_select_policy_pack | boolean | – | – |
| changed_files | – | – | – |
| context_profile | – | – | – |
| docs | – | – | – |
| execution_host | string | – | – |
| include_diff | boolean | – | – |
| policy_pack | – | – | – |
| project | string | yes | – |
| prompt | string | – | – |
| recipe | – | – | – |
| risk | string | – | – |
| run_dir | – | – | – |
| task | string | yes | – |
| validation_profile | – | – | – |
Structured output declared, but exposes no named fields.
No examples provided.
workbench_quality_gate ~66
Run the Workbench quality gate for a run directory.
| Name | Type | Req | Description |
|---|---|---|---|
| mode | string | – | – |
| project | string | yes | – |
| review_output | – | – | – |
| review_prompt | – | – | – |
| risk | – | – | – |
| run_dir | string | yes | – |
| validation_report | – | – | – |
Structured output declared, but exposes no named fields.
No examples provided.
workbench_record_execution ~87
Capture Goose/model response text into Workbench evidence artifacts.
| Name | Type | Req | Description |
|---|---|---|---|
| files_touched | – | – | – |
| follow_up | – | – | – |
| model_output_status | string | – | – |
| project | string | yes | – |
| response_source | string | – | – |
| response_text | string | yes | – |
| run_dir | string | yes | – |
| run_status | string | – | – |
| validation | – | – | – |
Structured output declared, but exposes no named fields.
No examples provided.
workbench_select_model ~117
Select a Workbench model tier and write model_selection.json.
| Name | Type | Req | Description |
|---|---|---|---|
| code_files | – | – | – |
| complexity_score | – | – | – |
| instruction_following | string | – | – |
| out | string | yes | – |
| project | string | yes | – |
| prompt | – | – | – |
| recipe | – | – | – |
| risk | string | yes | – |
| routing_feedback_path | – | – | – |
| task_text | – | – | – |
| task_type | string | yes | – |
| test_complexity_level | – | – | – |
| validation_profile | – | – | – |
| validation_strength | string | – | – |
Structured output declared, but exposes no named fields.
No examples provided.
workbench_select_policy_pack ~50
Recommend an advisory Workbench policy pack from task metadata.
| Name | Type | Req | Description |
|---|---|---|---|
| changed_files | – | – | – |
| prompt | – | – | – |
| risk | – | – | – |
| task_text | – | – | – |
| task_type | – | – | – |
Structured output declared, but exposes no named fields.
No examples provided.
workbench_validate_run ~61
Run deterministic Workbench validation over a run directory.
| Name | Type | Req | Description |
|---|---|---|---|
| changed_files | – | – | – |
| out_dir | string | yes | – |
| profile | – | – | – |
| project | string | yes | – |
| report_name | string | – | – |
| task_test_command | – | – | – |
Structured output declared, but exposes no named fields.
No examples provided.
What is the AI Workbench MCP server?
AI Workbench MCP is listed in the public MCP registry as io.github.hrishikesh-thakre/ai-workbench-mcp. Goose-first MCP server for Workbench-owned acceptance evidence, validation gates, and analytics. This page covers its PyPI package (ai-workbench-mcp).
Is the AI Workbench MCP server safe to use?
AI Workbench MCP scores 73 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 21 September 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 AI Workbench MCP server expose?
AI Workbench MCP exposes 7 tools: workbench_open_run, workbench_select_model, workbench_select_policy_pack, workbench_record_execution, workbench_validate_run, and 2 more. Their descriptions and schemas cost roughly 561 tokens of context every time the server is loaded.
Is the AI Workbench MCP server still maintained?
AI Workbench MCP is still listed as active in the MCP registry. We last reached this channel on 21 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.