MCP Server for Z.AI - A Model Context Protocol server that provides AI capabilities
Nothing to run from here
SyncytiumMD is installed from its publisher's own source and answers where it runs, so this marketplace is not in the path of a single call. There is no address here to send one to, and a panel that pretended otherwise would be showing you an answer we made up. Install it and call it from your own client — the Installation tab has the entry for each one.
94/100
trust score
24
tools declared
local
runs on your machine
—
downloads a day
What it does
One canonical context transpiled into Cursor, Claude, Copilot, Cline and more, with agent handoff.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user syncytiummd-mcp '--' npx -y syncytium-md mcp
# 2 — ask your agent for something these tools do
# syncytium-mcp, syncytium_get_context, syncytium_handoff and 21 more
SyncytiumMD costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Publishernot claimed
MRAll 1 server
mrcbrbn53611 server
1 category
Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.
Installation
Where are you running it?
Every route below installs the same thing and ends at the same approval screen. This one runs on your machine: your client starts SyncytiumMD as a process under your own user, with your files and your network, so the tool surface below is what it can do to your computer rather than to a server somewhere else. Its scan result is on the Security tab — read the surface before you approve it.
Claude Codedeclared by this listing
This is a public server: you run it yourself and this marketplace is not in the path. You need Node.js — the current LTS (24) is the safe choice; npx comes with it. Claude Code registers it in one command; --scope user makes it available in every project. The '--' is in quotes so that PowerShell passes it on.
claude mcp add --scope user syncytiummd-mcp '--' npx -y syncytium-md mcpReconnect, or start a new session, and the tools appear in the model’s tool list.
Free on mcprush, and it runs from its publisher’s own package: this marketplace is not in the path, so there is no key of ours to hold and no card to add.
What it writes
One config entry your client uses to start the process locally. A local server runs with your file system and your network, which is why it is priced without metering.
What you approve
24 tools, with what each one reads, writes and reaches shown before you agree — the same list on every route above. Read the tool surface.
Tool surface
What the model actually sees. Descriptions are diffed on every release — see version history.
Read from its source code. A server that builds its tool list when it starts can list more tools than this.
Canonical context bridge: one .syncytium/ source of truth transpiled into every AI coding tool, with a multi-agent handoff baton and a lease-based workspace lock.
No parameter schema on file.
Read-only. Get project rules, architecture, architectural decisions (ADR), and the active handoff state. Use this first in any session.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| topic | string | no | Optional filter; defaults to a compact overview |
| includeContent | boolean | no | Include full rule bodies instead of just id/title/description |
Write. Pass the baton to the next AI agent or record progress on the shared blackboard. Run this before you finish your turn.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| activeAgent | string | yes | Your name (e.g. Cursor, Claude Code, Antigravity) |
| nextAgent | string | no | Designated next agent, or omit |
| status | string | no | Current task state for the next agent |
| goal | string | no | Primary objective |
| completedWork | array | no | Work finished in this session |
| pendingTasks | array | no | Work the next agent must continue |
| touchedFiles | array | no | Files recently modified |
| notes | string | no | Context, warnings or rationale for the next agent |
| force | boolean | no | Ignore an active lease |
Write. Record an Architectural Decision (ADR) shared across all AI agents.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| id | string | no | ADR id; auto-allocated when omitted (ADR-002, ADR-003, …) |
| title | string | yes | Short imperative title of the decision |
| status | string | no | Lifecycle status of the ADR |
| context | string | yes | Background problem |
| decision | string | yes | The chosen solution |
| consequences | string | yes | Pros, cons and implications |
Destructive, but safe by default: previews the impact unless dryRun is false, requires confirm: true to delete, and archives the ADR so syncytium_restore can undo it.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| id | string | yes | ADR id to remove, e.g. ADR-003 |
| dryRun | boolean | no | Preview the impact without changing anything (default). |
| confirm | boolean | no | Must be true with dryRun:false to actually delete. |
Read-only. List recorded ADRs (optionally filtered by status or free-text query).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| status | string | no | Filter by ADR lifecycle status |
| query | string | no | Free-text search over title, context and decision |
| limit | number | no | Maximum number of ADRs to return |
Write. Add a new canonical rule to .syncytium/rules/ and regenerate every bridge file. Reversible with syncytium_remove_rule.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| id | string | no | kebab-case id; derived from the title when omitted |
| title | string | yes | Human-readable rule title |
| description | string | no | One-line summary shown in bridge files |
| body | string | yes | Markdown body of the rule |
| globs | array | no | Makes the rule glob-scoped instead of always-applied |
| tags | array | no | Tags used for grouping and search |
| alwaysApply | boolean | no | Force the rule into every session |
| sync | boolean | no | Regenerate bridge files afterwards |
Read-only. Search the canonical rule catalog by id, title, tag or body text.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| query | string | no | Free-text search; omit to list all rules |
Write. Edit an existing canonical rule in place (title, description, body, globs, tags).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| id | string | yes | Rule id to update |
| title | string | no | New human-readable title |
| description | string | no | New one-line summary |
| body | string | no | New Markdown body |
| globs | array | no | Replacement glob scope; pass [] to make the rule always-applied |
| tags | array | no | Replacement tag list |
| alwaysApply | boolean | no | Force the rule into every session |
| sync | boolean | no | Regenerate bridge files afterwards |
Destructive, but safe by default: previews the impact unless dryRun is false, requires confirm: true to delete, archives the rule, and prunes only banner-tagged generated files. Undo with syncytium_restore.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| id | string | yes | Rule id to remove |
| dryRun | boolean | no | Preview the impact without changing anything (default). |
| confirm | boolean | no | Must be true with dryRun:false to actually delete. |
Regenerate all AI tool bridge files (CLAUDE.md, .cursor/rules/, AGENTS.md, GEMINI.md, …). Can prune orphaned banner-tagged generated files; pass noPrune:true to keep them.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| targets | array | no | Restrict to specific adapter ids |
| force | boolean | no | Override an active workspace lease |
| noPrune | boolean | no | Do not remove orphaned generated files. |
Read-only. Get the multi-agent handoff audit trail: past goals, completed tasks and baton passes.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| limit | number | no | Maximum handoff entries to return |
Read-only. Validate canonical rules, frontmatter and ADR schema. Returns a compact summary, not the full report.
No parameter schema on file.
Read-only. Validate syncytium.config.json and every rule frontmatter against the zod schema and report issues without changing anything.
No parameter schema on file.
Write. Repair invalid config or rule frontmatter in place, then report what changed. Separate from syncytium_validate so a read-only scan can never mutate the workspace.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| dryRun | boolean | no | Report the repairs that would be applied without writing them. |
Read-only. Check context drift between .syncytium/ and the generated bridge files. Returns a summary plus the drifted paths.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| targets | array | no | Restrict the drift check to specific adapter ids |
Read-only. Run the full workspace health check: config, adapters, rules, drift, lock, git hook and CI gate. Never fixes or executes anything; remediation strings are suggestions only.
No parameter schema on file.
Write. Take the exclusive workspace lease so other agents do not edit the same files concurrently.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| agent | string | yes | Your agent name, recorded as the lease holder |
| goal | string | no | What you are working on while holding the lease |
| leaseMinutes | number | no | Lease length in minutes (1-1440) |
| force | boolean | no | Take over an existing lease |
Write. Release the workspace lease held by this agent (idempotent).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| agent | string | no | Only release the lease if it is held by this agent |
| force | boolean | no | Release a lease held by another agent |
Read-only. Report who currently holds the workspace lease and when it expires.
No parameter schema on file.
Read-only. Get the project knowledge graph (rules, tags, ADRs, agents, adapters, bridge files) for visualisation.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| category | string | no | Perspective to isolate before building the graph |
| compact | boolean | no | Hide file, directory and tag nodes for a smaller payload |
Write. Reverse-migrate existing unmanaged AI rule files (CLAUDE.md, .cursorrules, …) into .syncytium/. Dry-run by default; it only creates rules and never deletes the originals.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| dryRun | boolean | no | Report what would be imported without writing (default). |
Read-only. List recoverable deletions (archived rules and ADRs) with their archive timestamps, newest first.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| kind | string | no | Restrict to archived rules or archived ADRs |
| limit | number | no | Maximum number of entries to return |
Write. Restore an archived rule or ADR from the recoverable trash and regenerate bridge files. Fails if the same id already exists.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| kind | string | yes | Kind of archived item to restore |
| id | string | yes | Id of the archived rule or ADR |
Free
$0 forever
- Every tool, no call limit
- No card, and mcprush charges nothing for it
- Source published under MIT
- Runs on your machine — nothing of it reaches our gateway
- Nothing to cap, because mcprush bills nothing
What counts against your monthly calls
| Tool | Unit | Calls used | Out of the allowance |
|---|
Nothing here is billable: mcprush charges nothing to install SyncytiumMD or to call it, at any volume.
Call allowance · this installenforced at the gateway
Monthly allowance, in calls
—
—
Alert at 80% · then the tool returns a normal MCP error
Used this month: —
ATrust score 94 / 100
Release 0.3.1 · scanned 6 Nov 2026
Two independent axes, because powerful and malicious are different questions. The grade is threat only. The capability level is blast radius, and it is never a penalty on the grade — it is priced as one subtract-only term in the score, where you can see it.
Threat score100
Client score94
Findings1 threat · 0 capability
Capabilityhigh
Coveragesource
Verificationsource
Surface digest0fcf6a76c126d59b5928c17819ac4f69067f95b210dd766f986def5eede375c7
Score vectorthreat 100 → client 94
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | high | capability blast radius (high) — client exposure if the model is manipulated | −6 |
| verification-discount | source | publisher verification (provenance) — cryptographic build provenance ties the artifact to its source | −0 |
| coverage-honesty | source | inspection depth (source) — how much of the target the scan could see | −0 |
score = clamp(round(threatScore − E_cap − E_ver − E_cov), 0, 100). No model, no opinion, no network call at scoring time: the same methodology version against the same bytes always produces this number, and every line above is a field of the report rather than a summary of it.
What the scan could actually read
A grade is only as meaningful as its coverage, so the scanner publishes its own depth before it publishes its result.
Tool surfaceread
Implementation sourceread
Package metadataread
Live transportnot available
Tools were statically extracted from the published source (23 recovered), not enumerated from a running server. Tool-poisoning, Unicode-smuggling, capability and toxic-flow analysis ran on this inferred surface, but a mis-parsed registration could be missed or mis-attributed, so tool-derived findings are capped below “confirmed”. To grade the real runtime surface, scan the running server: --command "npx -y <package>".
Capability — what it could do if the model were manipulated
Tags derived from each tool’s schema and the implementation, not from what the tool calls itself. high is the level these add up to.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| syncytium_get_context | no tags | |
| syncytium_handoff | no tags | |
| syncytium_record_decision | no tags | |
| syncytium_remove_decision | no tags | |
| syncytium_list_decisions | no tags | |
| syncytium_create_rule | no tags | |
| syncytium_list_rules | no tags | |
| syncytium_update_rule | no tags | |
| syncytium_remove_rule | no tags | |
| syncytium_sync | no tags | |
| syncytium_get_history | no tags | |
| syncytium_lint | no tags | |
| syncytium_validate | no tags | |
| syncytium_validate_fix | no tags | |
| syncytium_diff | no tags | |
| syncytium_doctor | no tags | |
| syncytium_lock_acquire | no tags | |
| syncytium_lock_release | no tags | |
| syncytium_lock_status | no tags | |
| syncytium_get_graph | no tags | |
| syncytium_import | no tags | |
| syncytium_list_trash | no tags | |
| syncytium_restore | no tags |
Toxic-flow graph
The lethal trifecta, checked as a graph rather than as a checklist: untrusted input, a sensitive source and an external sink have to meet before there is a path worth worrying about.
The public result for this release does not print the flow graph, so there is nothing to show here. That is not the same as "no paths were found": what the scan did read is above, under coverage.
Supply chain and provenance
Integrityfirst-seen
Surface digest0fcf6a76c126d59b
Scanned2026-11-06
This is the first scan of this surface here, so there is nothing yet to compare it against.
Every result on this tab comes from one deterministic pass over the published package — offline, rule by rule, and auditable line by line above. Same methodology version, same bytes, same score.
Release history
Always latest — the install command names no version, so it installs the newest release when it runs; the current release on file is 0.3.1. Pin a release below and the command asks for exactly that one.
0.3.1
undated
latestNo release note was published with this version.
—
no reviews yet
Who can review
One review per account, from a signed-in account that does not publish this listing. Nothing else is asked — you can say what you think before you install it. Publishers can reply once per review, and a review can be edited or deleted by whoever wrote it.
Sign in to write one
Any signed-in account that does not publish SyncytiumMD can review it, once — before installing it or after. A review from an account that has installed it is marked as one.
No reviews yet
Nobody has reviewed this listing. The rating on the card is the mean of the reviews written here and nothing else, so there is no rating until somebody writes the first — which takes a signed-in account that does not publish it, and nothing else.