Keystash
PYPI · KEYSTASH
Keychain-backed secret broker: an AI agent can use your keys, but no tool ever returns one.
Available components
Last scanned (23 hours ago)
Scores higher than 80% of PyPI servers
Category Security
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 Security99
- No malware found by supply-chain analysis.Pass
- No known CVEs affecting this package version or its production dependencies.Pass
- Runs hatchling.build at install time, a recognised build step with no custom scripting around it. View diagnostics → Pass
- 3 of 12 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency71
- Repository check failed: the declared repository URL redirects; it must resolve directly. See how to fix → View diagnostics → Fail
- Cryptographically verified build provenance (signed, bound to thu-lawyer/keystash). View diagnostics → Pass
- Clear OSI-approved license (MIT).Pass
- Actively maintained (last published 27 days ago).Pass
- Disclosure check failed: no security disclosure policy was found in the source repository. See how to fix → Fail
Schema Quality & AI Usability62
- AI-judged instruction clarity (fair).Partial
- Tool/resource definitions use about 490 tokens (~81/item across 6 items; 6 tools + 0 resources), lean.Pass
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management70
- Stability observed for 21 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage81
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 43% of tool parameters carry a description.Partial
Tool Safety75
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- 0 of 2 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "secret_use" implies "send" and declares no destructiveHint at all, which the MCP spec reads as destructive by default. See how to fix → Fail
- An AI judge read all 6 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.
- 4 Nov 26 +16
- Malware scan: unverified → pass ▲ security
- 3 Nov 26 −15
- Malware scan: pass → unverified ▼ security
- Security disclosure: unverified → fail ▼ functional
- 2 Nov 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 60 to 63. That category is still filling its 30-day observation window: 18 days of observed history at the previous scan, 19 at this one. The score rises as the window fills, whether or not the server changes.
- 31 Oct 26 +1
- Security disclosure: fail → unverified ▼ functional
- 30 Oct 26 +15
- Malware scan: unverified → pass ▲ security
- 29 Oct 26 −15
- Malware scan: pass → unverified ▼ security
- 28 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 43 to 47. That category is still filling its 30-day observation window: 13 days of observed history at the previous scan, 14 at this one. The score rises as the window fills, whether or not the server changes.
- 26 Oct 26 +16
- Malware scan: unverified → 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 4 Nov 2026 · Analysed pypi/keystash@0.4.2
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 | thu-lawyer/keystash |
| Certificate issuer | https://token.actions.githubusercontent.com |
| Certificate SAN | https://github.com/thu-lawyer/keystash/.github/workflows/publish.yml@refs/tags/v0.4.2 |
| Rekor log index | 3140094003 |
| Predicate type | PyPI publish attestation https://docs.pypi.org/attestations/publish/v1 |
| Subject digest | sha256:8a78611f820dd423850ed17b13db1501d161de2df826cbc34ac352169ced478f |
Background: How many MCP packages publish verified provenance →
Install scripts 1 script
| Hook | Tier | Command |
|---|---|---|
| build_backend | allowlisted | hatchling.build |
Background: Why install scripts are a supply-chain risk →
Dependencies 12 packages
| Packages resolved | 12 |
|---|---|
| Stale | 3 |
| 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 →
secret_delete ~37
Delete a secret and its metadata. Requires a native confirmation dialog from the human; without it nothing is deleted.
| Name | Type | Req | Description |
|---|---|---|---|
| name | string | yes | – |
No output schema declared.
No examples provided.
secret_generate ~88
Generate a high-entropy value, store it, and return only a short fingerprint. The value is never returned; the human retrieves it with `keystash copy NAME` (clipboard, auto-cleared).
| Name | Type | Req | Description |
|---|---|---|---|
| allowed_urls | array | – | – |
| length | integer | – | – |
| name | string | yes | – |
| rotate_every_days | integer | – | – |
| tags | array | – | – |
No output schema declared.
No examples provided.
secret_list ~57
List stored secrets as metadata only: name, tags, rotation policy, last rotation, allowed URLs. Never returns a value.
| Name | Type | Req | Description |
|---|---|---|---|
| name | string | – | Return only this entry. |
| tag | string | – | Return only entries carrying this tag. |
No output schema declared.
No examples provided.
secret_rotate ~66
Replace an existing secret's value with a new one collected from the human through a native macOS dialog. Metadata is preserved unless overridden.
| Name | Type | Req | Description |
|---|---|---|---|
| allowed_urls | array | – | – |
| name | string | yes | – |
| rotate_every_days | integer | – | – |
| tags | array | – | – |
No output schema declared.
No examples provided.
secret_store ~136
Store a secret. The value is collected from the human through a native macOS dialog; it is never passed as an argument and never returned. Use this only when the human is present.
| Name | Type | Req | Description |
|---|---|---|---|
| allowed_urls | array | – | URL prefixes this entry may be sent to, each ending with '/'. secret_use refuses every other destination. |
| auth_header | string | – | Default 'Authorization'. |
| auth_prefix | string | – | Default 'Bearer '. |
| name | string | yes | Reference name, SERVICE_ENV_PURPOSE, e.g. OPENAI_PROD_KEY. |
| rotate_every_days | integer | – | – |
| tags | array | – | – |
No output schema declared.
No examples provided.
secret_use ~106
Send one HTTP request to an allow-listed URL with the entry's value as its credential. Returns the status and the scrubbed response body. The AI does not choose the credential and cannot read it.
| Name | Type | Req | Description |
|---|---|---|---|
| body | – | – | Request body: object, string, or omitted. |
| method | string | – | Default GET. |
| name | string | yes | – |
| timeout | number | – | Seconds, max 300. |
| url | string | yes | Must be covered by the entry's allowed_urls. |
No output schema declared.
No examples provided.
How do I install the Keystash MCP server?
Keystash runs locally as a PyPI package, launched with uvx keystash. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
pypi · keystash
claude mcp add thu-lawyer-keystash -- uvx keystash
What is the Keystash MCP server?
Keystash is an MCP server listed in the public MCP registry as io.github.thu-lawyer/keystash. Keychain-backed secret broker: an AI agent can use your keys, but no tool ever returns one. This page covers its PyPI package (keystash).
Is the Keystash MCP server safe to use?
Keystash scores 80 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 4 November 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 Keystash MCP server expose?
Keystash exposes 6 tools: secret_list, secret_store, secret_rotate, secret_generate, secret_use, secret_delete. Their descriptions and schemas cost roughly 490 tokens of context every time the server is loaded.
Is the Keystash MCP server still maintained?
Keystash is still listed as active in the MCP registry. We last reached this channel on 4 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 Keystash MCP server under?
Keystash declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.