katra
OCI · GHCR.IO/CRAIGJMIDWINTER/KATRA-MCP:0.1.0
A committed markdown dev log and task graph that agents read and write over MCP.
Available components
Last scanned (20 hours ago)
Scores higher than 89% of OCI servers
Category Productivity and Notes
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 Security0
- No malware scan is available for this kind of package: the supply-chain vendors we use do not cover it. This is a permanent gap in our coverage, not a finding about the package.Unverified
- Known CVEs could not be checked: this image's dependency list comes from an SBOM its publisher attached, which nothing verifies, so we will not report it as a clean result.Unverified
- Install-script risk not yet assessed.Unverified
- Dependency health could not be checked: this image's dependency list comes from an SBOM its publisher attached. It names packages and versions but not whether each is deprecated, still maintained or linked to its source, so there is nothing we can fairly grade.Unverified
Provenance & Transparency48
- 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 70 days ago).Pass
- Publishes a security disclosure policy (SECURITY.md).Pass
Schema Quality & AI Usability82
- AI-judged instruction clarity (excellent).Pass
- Tool/resource definitions use about 1088 tokens (~72/item across 15 items; 15 tools + 0 resources), lean.Pass
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management100
- No destabilizing schema changes in the last 30 days.Pass
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
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- We read all 15 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
- An AI judge read all 15 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities20
- Spec-recency check failed: implements MCP spec 2024-11-05; the latest is 2026-07-28. See how to fix → Fail
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 (12)
- Source repository
- Provenance
- License
- Maintenance
- Security disclosure
- Schema quality
- Stability
- Tool coverage
- Injection markers
- Destructive annotations
- Judged manipulation
- MCP protocol
Checks we could not complete (4)
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 Security (scores 0 for this)No malware scan is available for this kind of package: the supply-chain vendors we use do not cover it. This is a permanent gap in our coverage, not a finding about the package.
- Known CVEs in Supply Chain Security (scores 0 for this)Known CVEs could not be checked: this image's dependency list comes from an SBOM its publisher attached, which nothing verifies, so we will not report it as a clean result.
- Install scripts in Supply Chain Security (scores 0 for this)Install-script risk not yet assessed.
- Dependency health in Supply Chain Security (scores 0 for this)Dependency health could not be checked: this image's dependency list comes from an SBOM its publisher attached. It names packages and versions but not whether each is deprecated, still maintained or linked to its source, so there is nothing we can fairly grade.
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.
- 1 Nov 26 0
- Stability: 0.97 → pass security
- 31 Oct 26 0
- Stability: pass → 0.97 functional
- 16 Oct 26 0
- Stability: 0.97 → pass security
- 15 Oct 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.
- 13 Oct 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.
- 12 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 80 to 87. That category is still filling its 30-day observation window: 24 days of observed history at the previous scan, 26 at this one. The score rises as the window fills, whether or not the server changes.
- 10 Oct 26 −1
No change was recorded against any check on this day. Stability & Change Management went from 83 to 80.
- 4 Oct 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.
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 oci/ghcr.io/craigjmidwinter/katra-mcp:0.1.0
Provenance No attestation
The registry publishes no build provenance for this version, so there is nothing to verify.
| Result | No attestation |
|---|---|
| Ecosystem | oci |
| Reason | No attestation published |
Background: How many MCP packages publish verified provenance →
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 →
katra_append ~75
Append markdown to a draft. Defaults to the active draft if slug is omitted. Rich components are fenced code blocks: ```embed, ```compare, ```gallery, ```video, ```note, ```warning.
| Name | Type | Req | Description |
|---|---|---|---|
| markdown | string | yes | Markdown to append. |
| slug | string | – | Target entry slug (default: active draft). |
No output schema declared.
No examples provided.
katra_article_new ~55
Create a new article (evergreen reference) node. Returns its slug.
| Name | Type | Req | Description |
|---|---|---|---|
| body | string | – | Initial markdown body. |
| tags | string | – | Comma-separated tags. |
| title | string | yes | Article title. |
No output schema declared.
No examples provided.
katra_capture ~99
Import a media file (image/gif/video/html) into the dev log and append it to a draft. Use this for screenshots, animation gifs, and interactive html artifacts.
| Name | Type | Req | Description |
|---|---|---|---|
| as | string | – | Force kind: image|video|embed. |
| caption | string | – | Caption for the media. |
| path | string | yes | Path to the media file to import. |
| slug | string | – | Target entry slug (default: active draft). |
No output schema declared.
No examples provided.
katra_compare ~78
Import two images and append a before/after comparison slider to a draft.
| Name | Type | Req | Description |
|---|---|---|---|
| after | string | yes | Path to the 'after' image. |
| before | string | yes | Path to the 'before' image. |
| caption | string | – | Caption for the comparison. |
| slug | string | – | Target entry slug (default: active draft). |
No output schema declared.
No examples provided.
katra_decide ~78
Create a new decision (ADR) node. Returns its slug.
| Name | Type | Req | Description |
|---|---|---|---|
| body | string | – | Initial markdown body. |
| entry | string | – | The entry slug that recorded/occasioned this decision. |
| supersedes | string | – | Comma-separated decision slug(s) this one supersedes. |
| title | string | yes | Decision title. |
No output schema declared.
No examples provided.
katra_epic_new ~55
Create a new epic node. Returns its slug.
| Name | Type | Req | Description |
|---|---|---|---|
| body | string | – | Initial markdown body. |
| horizon | string | – | Planning horizon: now|next|later. |
| title | string | yes | Epic title. |
No output schema declared.
No examples provided.
katra_get ~32
Get one entry's frontmatter and raw markdown body by slug.
| Name | Type | Req | Description |
|---|---|---|---|
| slug | string | yes | The entry slug. |
No output schema declared.
No examples provided.
katra_list ~45
List dev log entries (newest first). Returns slug, title, date, draft status, hashes and tags.
| Name | Type | Req | Description |
|---|---|---|---|
| drafts_only | boolean | – | Only return unstamped drafts. |
No output schema declared.
No examples provided.
katra_new ~89
Create a new draft entry. Returns its slug. Write the *why*, not a paraphrased diff.
| Name | Type | Req | Description |
|---|---|---|---|
| body | string | – | Initial markdown body. |
| featured | boolean | – | Mark as a Deep Dive (long read). |
| summary | string | – | One-line summary for the index. |
| tags | string | – | Comma-separated tags. |
| title | string | yes | Entry title. |
No output schema declared.
No examples provided.
katra_nodes ~72
List nodes of a given type (newest first). Returns slug, title, type, date, status and other node-model fields. Omit type to list every node type.
| Name | Type | Req | Description |
|---|---|---|---|
| type | string | – | Node type to list: entry|task|epic|decision|article. Empty = all types. |
No output schema declared.
No examples provided.
katra_stamp ~72
Stamp a draft with its commit hash(es) + computed diffstat, moving it from In Progress into the log. Defaults to HEAD and the active draft.
| Name | Type | Req | Description |
|---|---|---|---|
| hashes | string | – | Comma-separated commit hash(es). Default: HEAD. |
| slug | string | – | Target entry slug (default: active draft). |
No output schema declared.
No examples provided.
katra_task_list ~47
List task nodes (newest first). Optionally filter by status.
| Name | Type | Req | Description |
|---|---|---|---|
| status | string | – | Filter to this status: todo|specced|doing|done|cut. |
No output schema declared.
No examples provided.
katra_task_new ~125
Create a new task node (status defaults to todo, or specced when spec is given). Returns its slug.
| Name | Type | Req | Description |
|---|---|---|---|
| body | string | – | Initial markdown body. |
| effort | string | – | Effort estimate: S|M|L. |
| epic | string | – | Parent epic slug. |
| spec | string | – | Spec artifact ref (a node slug in the katra, or a path relative to the repo root); creates the task already specced. |
| tags | string | – | Comma-separated tags. |
| title | string | yes | Task title. |
No output schema declared.
No examples provided.
katra_task_set_status ~59
Set a task's status (todo|specced|doing|done|cut).
| Name | Type | Req | Description |
|---|---|---|---|
| slug | string | yes | Task slug. |
| status | string | yes | New status: todo|specced|doing|done|cut. |
No output schema declared.
No examples provided.
katra_task_spec ~107
Attach a spec artifact to a task. Advances todo/empty status to specced; leaves doing/done/cut alone (setting spec never moves status backwards). A ref that resolves to neither a node nor a file warns but still writes — `katra doctor` is the blocking check, not this.
| Name | Type | Req | Description |
|---|---|---|---|
| ref | string | yes | Spec ref: a node slug in the katra, or a path relative to the repo root. |
| slug | string | yes | Task slug. |
No output schema declared.
No examples provided.
How do I install the katra MCP server?
katra runs locally as a container image, launched with docker run --rm -i ghcr.io/craigjmidwinter/katra-mcp:0.1.0. Ready-made configuration for Claude, Cursor, VS Code, Codex and 3 more is on this page, copied from each client's own documentation.
oci · ghcr.io/craigjmidwinter/katra-mcp:0.1.0
claude mcp add craigjmidwinter-katra -- docker run --rm -i ghcr.io/craigjmidwinter/katra-mcp:0.1.0
What is the katra MCP server?
katra is an MCP server listed in the public MCP registry as io.github.craigjmidwinter/katra. A committed markdown dev log and task graph that agents read and write over MCP. This page covers its container image (ghcr.io/craigjmidwinter/katra-mcp:0.1.0).
Is the katra MCP server safe to use?
katra scores 53 out of 100 on VerifyMCP. 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 katra MCP server expose?
katra exposes 15 tools: katra_append, katra_article_new, katra_capture, katra_compare, katra_decide, and 10 more. Their descriptions and schemas cost roughly 1,088 tokens of context every time the server is loaded.
Is the katra MCP server still maintained?
katra 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 katra MCP server under?
katra 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 katra MCP server?
VerifyMCP ran 12 checks on katra, covering Source repository, Provenance, License, Maintenance and 8 more. 4 items could not be completed, a gap on our side rather than a finding about katra: Malware scan, Known CVEs, Install scripts and Dependency health. 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 container image, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.