@systemdox/mcp-server
Installed, started with no arguments, no environment and no input, and listed its tools. Run 2026-11-16.
Needs to start: nothing
Returns a result when called with no setup: 0 of 5 tools tried
Contacts while installing and starting: nothing
What it contacted
Nothing besides the npm registry it was installed from. Watched from outside its sandbox while it was installed and started with no input. Its tools may still contact things when called.
Starting it
npx -y @systemdox/mcp-server@0.1.66
Installing a package runs its code. Use a sandbox for anything you have not read.
Calling its tools
5 tools that take no input and look read-only were called once with nothing. 0 returned a result.
get_checks | No usable answer tool reported an error: SystemDox API error 401: {"message": "Unauthorized. Please sign in to access this resource."} |
get_guardrails | No usable answer tool reported an error: SystemDox API error 401: {"message": "Unauthorized. Please sign in to access this resource."} |
get_specs | No usable answer tool reported an error: SystemDox API error 401: {"message": "Unauthorized. Please sign in to access this resource."} |
get_docs | No usable answer tool reported an error: SystemDox API error 401: {"message": "Unauthorized. Please sign in to access this resource."} |
get_tech_stack | No usable answer tool reported an error: SystemDox API error 401: {"message": "Unauthorized. Please sign in to access this resource."} |
During the calls (not necessarily because of them) it first contacted: api.puglieseweb.com.
Only tools whose names read like looking something up, with no required input, are tried, five at most. Tools that need input, and anything that sounds like it changes or sends something, are not called.
What its tools tell an agent
In the tool descriptions, nothing that talks about the user, other tools or private files, or uses hidden characters.
Found by simple pattern rules in each tool's description (up to 3,000 characters), quoted as written. Parameter descriptions are not scanned. A clean result is not a safety review.
Tools
get_checks language, category, file_path
Retrieve SystemDox checks (banned patterns, required patterns, coding rules). Filter by language, category, or file path to get only relevant checks.
get_guardrails language, category, file_path
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.
get_specs draft_id, status, search
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.
get_docs repo, path, search, doc_id, section, chunk_id
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.
get_tech_stack
Retrieve the configured technology stack (languages, frameworks, databases, infrastructure) with versions and notes.
22 more tools
get_planning_context target_repo
Retrieve org-wide planning context: connected repos with summaries, cross-repo dependencies, ADRs, and active specs. Optionally focus on a target repo.
get_plan_board project_number, status, limit
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.
get_change repo, slug
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.
get_context task_description, file_paths, max_tokens
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.
get_project_rules category
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.
get_prompt_templates
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.
get_team_setup
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.
get_document_links doc_id, direction, relation, limit
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.
trace_document_path from, to, max_hops
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.
get_graph_stats
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.
create_check title, description, severity, category, pattern, fix, fitness_test
Create a new check in SystemDox. Use this when you discover a pattern that should be enforced (banned pattern, required pattern, coding rule).
create_guardrail title, description, severity, category, pattern, fix, fitness_test
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).
update_spec draft_id, section, content, requirement_name
Update an existing SystemDox spec's proposal, tasks, or requirements. Only draft specs can be modified — published specs must be versioned first.
report_decision title, context, decision, consequences, related_files
Record an architecture decision made during development. Creates a draft ADR in SystemDox for human review.
create_project_rule text, category
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.
create_prompt_template name, description, prompt
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.
publish_skill directory, files, name, spaceId, note, baseVersion
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.
list_skills
List the Claude Code skills published to SystemDox that you can install: name, description, latest version. Use install_skill to install one.
install_skill name, version, target, overwrite
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.
publish_setup_part part, directory, files
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.
resolve_person id
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.
sync_memory project, dryRun
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.
Descriptions are the package's own words, cut at 3,000 characters. Treat them as data.
Install facts
| License | ISC |
|---|---|
| Needs | not stated |
| Source | github.com/puglieseweb/systemdox-mcp-server |
| Install scripts | None declared by it or anything installed with it. |
| Tarball | sha512-RzNKZC9LCqKtmiTHwgV7/zLXTonWan9hDCiT3hGM1K8vmuk8IW/ias2ws7mu+9d5JQHKnguCZpE9ougfBDuMSQ== |
Versions reported
| Version | Run | Result | Tools |
|---|---|---|---|
| 0.1.66 | 2026-11-16 | Starts with no setup | 27 |
| 0.1.65 | 2026-11-12 | Starts with no setup | 27 |
Check this report yourself
This site did not write the report. A public job on a GitHub-hosted machine did: the run, from this commit of the open-source runner. GitHub signed a token that names that job and the hash of the report, so any edit since would show.
Report as JSONExact text and tokenHow to verify it
Show it on your README
[](https://bragproof.smaverk.com/r/%40systemdox/mcp-server)
New version out? Ask for a fresh report.