PromptBranch
NPM · @PROMPTBRANCH/MCP
Local-first MCP server for versioning, searching, evaluating, and improving AI prompts.
Available components
Last scanned (15 hours ago)
Scores higher than 63% of npm servers
Category AI and Machine Learning
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 Security81
- No malware found by supply-chain analysis.Pass
- CVE check failed: a known high-severity CVE affects zod 3.25.76, a direct dependency. A fixed version is available. View diagnostics → Fail
- No install/post-install scripts declared.Pass
- 32 of 101 dependencies flagged as unhealthy. View diagnostics → Partial
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 63 days ago).Pass
- Publishes a security disclosure policy (SECURITY.md).Pass
Schema Quality & AI Usability75
- AI-judged instruction clarity (good).Pass
- Tool/resource definitions use about 561 tokens (~93/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 Management100
- No destabilizing schema changes in the last 30 days.Pass
Tool Coverage89
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 67% 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 6 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
- 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
Checks we ran (16)
- Malware scan
- Known CVEs
- Install scripts
- Dependency health
- Source repository
- Provenance
- License
- Maintenance
- Security disclosure
- Schema quality
- Stability
- Tool coverage
- Injection markers
- Destructive annotations
- Judged manipulation
- MCP protocol
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.
- 19 Nov 26 +1
- Stability: 0.97 → pass security
- 18 Nov 26 0
- Security disclosure: unverified → pass ▲ functional
- Stability: pass → 0.97 functional
- 17 Nov 26 −1
- Security disclosure: pass → unverified ▼ functional
- 12 Nov 26 +1
- Stability: 0.97 → pass security
- 11 Nov 26 +1
- Security disclosure: unverified → pass ▲ functional
- 10 Nov 26 0
- Security disclosure: pass → unverified ▼ functional
- 9 Nov 26 +5
- Source repository: unverified → pass ▲ security
- 8 Nov 26 −6
- Provenance: pass → unverified ▼ security
- Security disclosure: unverified → pass ▲ functional
- Stability: pass → 0.87 functional
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 Nov 2026 · Analysed npm/@promptbranch/mcp@0.2.6
Provenance No attestation
The registry publishes no build provenance for this version, so there is nothing to verify.
| Result | No attestation |
|---|---|
| Ecosystem | npm |
Background: How many MCP packages publish verified provenance →
Vulnerabilities 1 finding
| ID | CVE | Severity | Vector | Fix available |
|---|---|---|---|---|
| GHSA-mrhx-c7xc-m3w5 | CVE-2023-54404 | high | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H | yes |
Background: What a vulnerability scan can and cannot prove →
Dependencies 101 packages
| Packages resolved | 101 |
|---|---|
| Stale | 31 |
| 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 →
add_note ~66
Attach a freeform note to a prompt (or a specific version of it).
| Name | Type | Req | Description |
|---|---|---|---|
| body | string | yes | – |
| prompt | string | yes | Prompt title (exact or unique substring) or id |
| versionId | string | – | Specific version id; omit for a prompt-level note |
No output schema declared.
No examples provided.
get_prompt ~150
Fetch and render a prompt. If status is needs_input, do not execute content: ask the user for every missingVariables value, then call get_prompt again with variables. Execute content only when status is ready. Defaults to the current (preferred) version; pin with version and/or branch.
| Name | Type | Req | Description |
|---|---|---|---|
| branch | string | – | Branch name; defaults to the current version's branch |
| prompt | string | yes | Prompt title (exact or unique substring) or id |
| variables | object | – | Values for {{variables}}. If the response says needs_input, ask the user for every missing variable and call get_prompt again. |
| version | integer | – | Per-branch version number; defaults to the current version |
No output schema declared.
No examples provided.
list_prompts ~36
List prompts in the library, optionally filtered by collection or tag.
| Name | Type | Req | Description |
|---|---|---|---|
| collection | string | – | – |
| tag | string | – | – |
No output schema declared.
No examples provided.
report_run ~133
Report that a prompt version was used: which tool/model ran it, the outcome rating (1–5) and a short result summary.
| Name | Type | Req | Description |
|---|---|---|---|
| metrics | object | – | Arbitrary structured metrics (tokens, latency…) |
| model | string | – | – |
| outcomeRating | integer | – | – |
| prompt | string | yes | Prompt title (exact or unique substring) or id |
| resultSummary | string | – | – |
| tool | string | yes | Tool that ran the prompt, e.g. 'kimi-cli', 'mcp' |
| version | integer | – | Per-branch version number; defaults to the current version |
No output schema declared.
No examples provided.
search_prompts ~75
Full-text search over prompt titles, descriptions, tags, notes and version content.
| Name | Type | Req | Description |
|---|---|---|---|
| collection | string | – | Restrict to this collection (name) |
| limit | integer | – | Max results (default 10) |
| query | string | yes | – |
| tag | string | – | Restrict to prompts carrying this tag (name) |
No output schema declared.
No examples provided.
suggest_variation ~101
Propose a rewritten version of a prompt. Creates a PENDING suggestion that a human must approve in the PromptBranch app before it becomes usable — agents propose, humans approve.
| Name | Type | Req | Description |
|---|---|---|---|
| baseVersion | integer | – | Version number to base the suggestion on; defaults to current |
| newContent | string | yes | – |
| prompt | string | yes | Prompt title (exact or unique substring) or id |
| rationale | string | yes | Why this change improves the prompt |
No output schema declared.
No examples provided.
How do I install the PromptBranch MCP server?
PromptBranch runs locally as an npm package, launched with npx -y @promptbranch/mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
npm · @promptbranch/mcp
claude mcp add promptbranch-promptbranch -- npx -y @promptbranch/mcp
What is the PromptBranch MCP server?
PromptBranch is an MCP server listed in the public MCP registry as io.github.PromptBranch/promptbranch. Local-first MCP server for versioning, searching, evaluating, and improving AI prompts. This page covers its npm package (@promptbranch/mcp).
Is the PromptBranch MCP server safe to use?
PromptBranch scores 79 out of 100 on VerifyMCP. We recorded 1 known advisory against it as of 21 November 2026. It declares no install or post-install scripts. 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 PromptBranch MCP server expose?
PromptBranch exposes 6 tools: get_prompt, search_prompts, list_prompts, report_run, add_note, suggest_variation. Their descriptions and schemas cost roughly 561 tokens of context every time the server is loaded.
Is the PromptBranch MCP server still maintained?
PromptBranch is still listed as active in the MCP registry. We last reached this channel on 21 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 PromptBranch MCP server under?
PromptBranch 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 PromptBranch MCP server?
VerifyMCP ran 16 checks on PromptBranch, covering Malware scan, Known CVEs, Install scripts, Dependency health and 12 more. Endpoint Security and Transport & Reachability do not apply to an npm package, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.