Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

io.github.puglieseweb/systemdox

NPM · @SYSTEMDOX/MCP-SERVER

Your architecture in your agents' context: checks, specs, ADRs and docs over MCP, at write time.

+4 this week 71 Trust /100

Last scanned (18 hours ago)

Scores higher than 42% of npm servers

Category Developer Tools

Trust breakdown (7 categories)

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
  • 30 of 93 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency45
Schema Quality & AI Usability72
  • AI-judged instruction clarity (good).Pass
  • Context-footprint check failed: tool/resource definitions use about 3470 tokens (~119/item across 29 items; 29 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management57
  • Stability observed for 17 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
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 Safety83
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • 1 of 3 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "publish_skill" implies "publish" and declares no destructiveHint at all, which the MCP spec reads as destructive by default. See how to fix → Partial
  • An AI judge read all 30 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
What we tested

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 →

Changelog

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 Nov 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 50 to 53. That category is still filling its 30-day observation window: 15 days of observed history at the previous scan, 16 at this one. The score rises as the window fills, whether or not the server changes.

  • 19 Nov 26 +1
    • Destructive annotations: 0% → 33% ▲ functional
    • Package version: 0.1.66 → 0.1.67 functional
  • 17 Nov 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 40 to 43. That category is still filling its 30-day observation window: 12 days of observed history at the previous scan, 13 at this one. The score rises as the window fills, whether or not the server changes.

  • 16 Nov 26 0
    • Stability: 0.37 → unverified ▼ security
    • Tool safety: pass → unverified ▼ security
    • Capabilities: pass → unverified ▼ functional
    • Tool coverage: 100 → unverified ▼ functional
    • Schema quality: Schema quality not yet verified: we do not have a sandbox capture of the MCP schema this version of the package serves yet. functional
    • Package version: 0.1.65 → 0.1.66 functional
  • 15 Nov 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 33 to 37. That category is still filling its 30-day observation window: 10 days of observed history at the previous scan, 11 at this one. The score rises as the window fills, whether or not the server changes.

  • 13 Nov 26 +1
    • Security disclosure: unverified → fail ▼ functional
  • 12 Nov 26 0
    • Security disclosure: fail → unverified ▼ functional
  • 11 Nov 26 +16
    • Malware scan: unverified → pass ▲ security
Diagnostics

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/@systemdox/mcp-server@0.1.67

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 93 packages
Packages resolved 93
Stale 30
Tree resolution Complete

Background: SBOMs and build attestations, explained →

MCP tools · 29 exposed · ~3,407 tokens

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 →

Tool Tokens
create_check ~131

Create a new check in SystemDox. Use this when you discover a pattern that should be enforced (banned pattern, required pattern, coding rule).

NameTypeReqDescription
categorystring–Category (defaults to conventions)
descriptionstringyesDetailed description of what the check enforces and why
fitness_teststring–Shell command to detect violations in CI
fixstring–Correct code pattern to use instead
patternstring–Bad code pattern that should be avoided
severitystringyesSeverity level
titlestringyesShort title for the check

No output schema declared.

No examples provided.

create_guardrail ~160

DEPRECATED — use `create_check` instead. This name still works and will not be removed before 2027-01-31. Create a new check in SystemDox. Use this when you discover a pattern that should be enforced (banned pattern, required pattern, coding rule).

NameTypeReqDescription
categorystring–Category (defaults to conventions)
descriptionstringyesDetailed description of what the check enforces and why
fitness_teststring–Shell command to detect violations in CI
fixstring–Correct code pattern to use instead
patternstring–Bad code pattern that should be avoided
severitystringyesSeverity level
titlestringyesShort title for the check

No output schema declared.

No examples provided.

create_project_rule ~78

Create a new project rule in SystemDox Standards. Use this when you discover a team principle or convention that should be enforced across the project.

NameTypeReqDescription
categorystringyesRule category
textstringyesThe rule statement — one enforceable principle per rule (e.g. 'All deployments MUST go through GitHub Actions workflows')

No output schema declared.

No examples provided.

create_prompt_template ~89

Create a new reusable prompt template in SystemDox Standards. Use this to store preconfigured prompts for common AI tasks like code reviews, documentation generation, or analysis frameworks.

NameTypeReqDescription
descriptionstring–Brief description of when to use this template
namestringyesShort name for the template
promptstringyesThe full prompt text that Gen AI will use when generating content

No output schema declared.

No examples provided.

delete_project_rule ~73

Delete a project rule from SystemDox Standards by its id (get_project_rules shows each rule's id). Use this when a rule no longer holds; no session sees it afterwards.

NameTypeReqDescription
idstringyesThe rule's id, as get_project_rules shows it (e.g. 'rul_…')

No output schema declared.

No examples provided.

get_change ~205

Read one change (a specs/changes/<slug>/ folder of a connected repository) as SystemDox last synced it from GitHub: the state of each part of its brief (decision, contract, behaviour, plan) and of its release, each with its pull request; the decision's ADR and status; the contract files; every feature file that names the change, with its scenarios as id · state · title; the plan (plan.md, the draft, the board); the release pull requests; and the Change object as JSON. The last line says "The brief is passed" or "The brief is not passed: <part> is <state>". Call it before building a story, and stop if the brief is not passed or the story's scenarios are not proposed. Read-only.

NameTypeReqDescription
repostringyesThe repository that holds the change, as owner/name
slugstringyesThe change's folder name: specs/changes/<slug>/

No output schema declared.

No examples provided.

get_checks ~110

Retrieve SystemDox checks (banned patterns, required patterns, coding rules). Filter by language, category, or file path to get only relevant checks.

NameTypeReqDescription
categorystring–Filter by category (imports, auth, error-handling, architecture, testing, security, conventions, data-access)
file_pathstring–File path being edited — language is auto-detected from the extension
languagestring–Filter by programming language (python, typescript, javascript, cloudformation)

No output schema declared.

No examples provided.

get_context ~136

Intelligent context aggregator: fetches checks, specs, docs, and tech stack, ranks them by relevance to your current task, and returns the full text of the highest-ranked items within a token budget — each with the ID needed to fetch the rest. Use this instead of calling individual tools when you want curated, relevant context.

NameTypeReqDescription
file_pathsarray–File paths being edited — used for language/category detection
max_tokensnumber–Maximum token budget for the response (default: 4000)
task_descriptionstringyesWhat you're working on (e.g., 'add a new REST endpoint for user preferences')

No output schema declared.

No examples provided.

get_docs ~173

Retrieve synced documentation from connected GitHub repositories. Filter by repo, file path pattern, or keyword search. Pass doc_id with section (a heading anchor) or chunk_id to retrieve just that section instead of the whole document.

NameTypeReqDescription
chunk_idstring–Section chunk id ('{path_hash}#{anchor}') from get_context — with doc_id, returns just that section
doc_idstring–Specific document ID to retrieve full content
pathstring–File path glob pattern (e.g., docs/adr/*.md)
repostring–Filter by repo (owner/repo format)
searchstring–Keyword search across document content
sectionstring–Heading anchor (e.g. 'rollback-strategy') — with doc_id, returns just that section

No output schema declared.

No examples provided.

get_document_links ~152

What one document links to and from, strongest first. Each link says how it is known: declared (a person made it), extracted (the file says so), or inferred (a reading that could be wrong), with a confidence and the file and line it came from. A reference that could mean several documents is listed as ambiguous with its candidates, and is never drawn as a link. doc_id is the id get_docs returns. Read-only.

NameTypeReqDescription
directionstring–Default both
doc_idstringyesA document id, as get_docs returns it
limitinteger–Most links to show (default 50)
relationstring–Only links of this kind

No output schema declared.

No examples provided.

get_graph_stats ~58

The state of the graph: links counted by how they are known, each repository's freshness (marked BEHIND when a push has not finished indexing), and how repositories depend on each other, from the files that declare it. Read-only.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

get_guardrails ~139

DEPRECATED — use `get_checks` instead. This name still works and will not be removed before 2027-01-31. Retrieve SystemDox checks (banned patterns, required patterns, coding rules). Filter by language, category, or file path to get only relevant checks.

NameTypeReqDescription
categorystring–Filter by category (imports, auth, error-handling, architecture, testing, security, conventions, data-access)
file_pathstring–File path being edited — language is auto-detected from the extension
languagestring–Filter by programming language (python, typescript, javascript, cloudformation)

No output schema declared.

No examples provided.

get_plan_board ~177

Read the GitHub Projects boards connected to this workspace. With no arguments, lists the open boards with their item counts by status. With project_number, lists that board's issues grouped by status (In Progress / Todo / Done), each with issue number, title, repo, labels, assignees and URL — so you can see what is planned or in flight and pick up the right issue. Read-only: this tool cannot create, move, or close board items.

NameTypeReqDescription
limitinteger–Max items to list (default 50). Group headings always show the true totals.
project_numberinteger–Board number (the N in github.com/orgs/{org}/projects/N). Omit to list the open boards.
statusstring–With project_number, return only the items in this status group

No output schema declared.

No examples provided.

get_planning_context ~70

Retrieve org-wide planning context: connected repos with summaries, cross-repo dependencies, ADRs, and active specs. Optionally focus on a target repo.

NameTypeReqDescription
target_repostring–Focus on a specific repo (owner/repo format) to get its CLAUDE.md and relevant context

No output schema declared.

No examples provided.

get_project_rules ~56

Retrieve project rules defined in SystemDox Standards. These are team-defined principles covering deployment, architecture, security, testing, and process. Filter by category to get only relevant rules.

NameTypeReqDescription
categorystring–Filter by rule category

No output schema declared.

No examples provided.

get_prompt_templates ~48

Retrieve reusable prompt templates from SystemDox Standards. These are preconfigured prompts that Gen AI should use when generating content — e.g. code review checklists, documentation templates, or analysis frameworks.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

get_specs ~85

Retrieve SystemDox specifications (proposal, requirements with RFC 2119 keywords, Given/When/Then scenarios). Get a specific spec by ID, filter by status, or search by keyword.

NameTypeReqDescription
draft_idstring–Specific spec ID to retrieve with full content
searchstring–Keyword search across spec names
statusstring–Filter by status

No output schema declared.

No examples provided.

get_team_setup ~55

What this workspace's team setup holds (skills, plugin, hooks, MCP servers, memory) and what this computer lacks, with what to do about it. Call it to check whether this computer is set up. Reads only.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

get_tech_stack ~29

Retrieve the configured technology stack (languages, frameworks, databases, infrastructure) with versions and notes.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

install_skill ~122

Install a skill published to SystemDox onto this computer (default ~/.claude/skills/<name>/). Refuses, naming the files, when a file there was edited since it was installed, unless overwrite is true. Never runs anything.

NameTypeReqDescription
namestringyesThe skill's name
overwriteboolean–Replace files edited since they were installed
targetstring–Folder to install into, e.g. a repo's .claude/skills/<name>
versioninteger–A version number (default: the latest)

No output schema declared.

No examples provided.

list_skills ~38

List the Claude Code skills published to SystemDox that you can install: name, description, latest version. Use install_skill to install one.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

publish_setup_part ~249

Publish one part of your team's Claude Code setup to SystemDox: `hooks` (hooks/hooks.json and the scripts/ it calls), `mcp` (.mcp.json), `agents` (agents/*.md), `commands` (commands/*.md) or `instructions` (CLAUDE.md). Every part but instructions makes a new version of the team plugin, which each member accepts at their next update. Publishing hooks, mcp, agents or commands needs the admin role. Pass `directory`: the server reads only the files the part accepts, byte for byte, and refuses a link, a binary file or a file too large before anything is sent. Never retype the files into `files` when the folder is on this computer.

NameTypeReqDescription
directorystring–The folder on this computer: for hooks, the one holding hooks/hooks.json and scripts/; for mcp, the one holding .mcp.json; for instructions, the one holding CLAUDE.md; for agents or commands, the one…
filesarray–Only when there is no folder to read
partstringyesWhich part of the setup

No output schema declared.

No examples provided.

publish_skill ~243

Publish a Claude Code skill folder (SKILL.md plus its references and scripts) to SystemDox so it can be installed on any computer. Pass `directory` (e.g. ~/.claude/skills/<name>): the server reads the files itself, byte for byte. Publishing a name again makes a new version. Never retype the files into `files` when the folder is on this computer.

NameTypeReqDescription
baseVersioninteger–The version these files were edited from. When given, the publish is refused (SYD-K017) if someone published a newer version since, instead of replacing their changes
directorystring–The skill folder on this computer, holding SKILL.md at its root
filesarray–Only when there is no folder to read
namestring–The skill's name; defaults to SKILL.md's frontmatter name and must match it
notestring–A short change note for this version, shown in the console's history (e.g. "Fix the GA4 step")
spaceIdstring–Space for a NEW skill (default: your default space)

No output schema declared.

No examples provided.

report_decision ~112

Record an architecture decision made during development. Creates a draft ADR in SystemDox for human review.

NameTypeReqDescription
consequencesstringyesWhat this decision means going forward — trade-offs, follow-up work
contextstringyesWhat prompted this decision — the problem or constraint
decisionstringyesWhat was decided and why
related_filesarray–File paths related to this decision
titlestringyesDecision title (e.g., 'Use WebSocket for real-time updates')

No output schema declared.

No examples provided.

resolve_person ~124

Read back a person that a team memory names by identifier, written as `con_…` (label), `ctc_…` or `usr_…`: their label, name, phone number and email address, from the vault that holds them. The details are for this session only: never write them into a memory file; the memory keeps the identifier. Writes nothing.

NameTypeReqDescription
idstringyesThe identifier, e.g. con_01JC2Q8Y4M7T0X3K5N9P2R6S8V

No output schema declared.

No examples provided.

sync_memory ~172

Sync one project's team memory on this computer with SystemDox: pull the files the team changed, push the ones changed here, keep both texts of a file changed on both sides. It never answers for a person: a file that still holds a phone number, an email address or a home-folder path is skipped and listed, with the command for the member to run in their own terminal (`npx -y @systemdox/mcp-server sync-memory`). Pass dryRun to see what it would do without writing or sending anything.

NameTypeReqDescription
dryRunboolean–Show what would be pulled, pushed, deleted, conflicted and skipped, and change nothing
projectstring–The project's team memory, e.g. puglieseweb-ltd; needed when the workspace has more than one

No output schema declared.

No examples provided.

trace_document_path ~96

The shortest way two documents connect, walking links in either direction. Each step says how it is known, and the path is only as strong as its weakest step. Read-only.

NameTypeReqDescription
fromstringyesA document id, as get_docs returns it
max_hopsinteger–Longest path to look for (default 6)
tostringyesA document id, as get_docs returns it

No output schema declared.

No examples provided.

update_project_rule ~123

Change a project rule in SystemDox Standards by its id (get_project_rules shows each rule's id). Give new words, a new category, or both; the rule keeps its id. Use this when a rule is out of date or filed under the wrong category.

NameTypeReqDescription
categorystring–The rule's new category
idstringyesThe rule's id, as get_project_rules shows it (e.g. 'rul_…')
textstring–The rule's new words — one enforceable principle, not blank

No output schema declared.

No examples provided.

update_spec ~104

Update an existing SystemDox spec's proposal, tasks, or requirements. Only draft specs can be modified — published specs must be versioned first.

NameTypeReqDescription
contentstringyesNew markdown content for the section. For requirements, provide the full requirement content.
draft_idstringyesID of the spec to update
requirement_namestring–Name of the requirement (required when section is 'requirements')
sectionstringyesWhich section to update

No output schema declared.

No examples provided.

Install

How do I install the io.github.puglieseweb/systemdox MCP server?

io.github.puglieseweb/systemdox runs locally as an npm package, launched with npx -y @systemdox/mcp-server. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

npm · @systemdox/mcp-server

# add to Claude Code
claude mcp add puglieseweb-systemdox -- npx -y @systemdox/mcp-server
Common questions

What is the io.github.puglieseweb/systemdox MCP server?

io.github.puglieseweb/systemdox is an MCP server listed in the public MCP registry as io.github.puglieseweb/systemdox. Your architecture in your agents' context: checks, specs, ADRs and docs over MCP, at write time. This page covers its npm package (@systemdox/mcp-server).

Is the io.github.puglieseweb/systemdox MCP server safe to use?

io.github.puglieseweb/systemdox scores 71 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 io.github.puglieseweb/systemdox MCP server expose?

io.github.puglieseweb/systemdox exposes 29 tools: get_checks, get_guardrails, get_specs, get_docs, get_tech_stack, and 24 more. Their descriptions and schemas cost roughly 3,407 tokens of context every time the server is loaded.

Is the io.github.puglieseweb/systemdox MCP server still maintained?

io.github.puglieseweb/systemdox 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 io.github.puglieseweb/systemdox MCP server under?

io.github.puglieseweb/systemdox declares the ISC 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 io.github.puglieseweb/systemdox MCP server?

VerifyMCP ran 16 checks on io.github.puglieseweb/systemdox, 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.