MCP Server for Z.AI - A Model Context Protocol server that provides AI capabilities
Nothing to run from here
Forge Delegate 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.
87/100
trust score
9
downloads a day
local
runs on your machine
2k
downloads in 30d
What it does
Delegate coding tasks from Claude Code, Codex or opencode to any model opencode can run.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user forge-delegate-mcp '--' npx -y forge-delegate serve
# 2 — ask your agent for something these tools do
# list_models, ask_model, delegate and 3 more
Forge Delegate costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Publishernot claimed
MUAll 1 server
MuhamadBarzani1 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 Forge Delegate 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 forge-delegate-mcp '--' npx -y forge-delegate serveReconnect, 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
6 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.
List the models available for delegation: local/keyless ones, direct-API models from opencode logins, and agentic models from the local opencode installation. Call it when the user asks what's available or wants to change the default model, not before an ordinary delegation — those use the…
No parameter schema on file.
Get a second opinion from a different model — on a design, an approach, or a tricky snippet — or ask one when the user requests it. Sends a one-shot prompt over a direct API call and returns the raw response. The model has no file access and cannot take actions; for anything touching files use…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| model | string | no | provider/model or ollama:<name>, e.g. deepseek/deepseek-v4-flash, ollama:llama3. Omit to use the configured default; don't pick a premium tier |
| prompt | string | yes | The full question. The model has seen none of this conversation, so include the code and context it needs |
| system | string | no | Optional system prompt, e.g. a role or an answer format |
Hand a coding task to another AI model running as a full agent via local opencode: it reads the project, explores, and writes the code in its own tool loop, none of which enters your context. Use it instead of writing the code yourself for: tests for code that already exists; a mechanical refactor…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| model | string | no | provider/model, e.g. opencode/deepseek-v4.1-flash-free. Omit to use the configured default; don't raise it to a premium tier — split the task instead |
| task | string | yes | Self-contained instructions: the goal, the file paths to read or change, constraints, and how to check the result (e.g. which tests to run). The agent has not seen this conversation |
| files | array | no | Paths to attach to the agent's prompt (inline only; ignored with background:true). Rarely needed: the agent reads paths named in task itself |
| background | boolean | no | Run detached and return a job id immediately; poll check_delegation (default false) |
| continue_session | string | no | Session id from a previous delegation's result, to continue in that agent session |
| directory | string | no | Absolute path of the project to work in (defaults to config defaultDirectory, else the server's working directory) |
| agent | string | no | opencode agent to use (defaults to config defaultAgent) |
| autoApprove | boolean | no | Let the agent edit files and run commands without asking (defaults to config autoApprove, true). When false nobody is there to approve, so actions that need approval can stall or be refused |
| profile | string | no | Named preset from config profiles (see get_delegate_config) that sets model, agent, variant, directory and autoApprove together |
Check a delegation started with background:true. Returns RUNNING, DONE or TIMED OUT, the elapsed time, the session id, and the last 8,000 characters of the agent's output. Each poll costs context, so wait between polls instead of checking in a tight loop. Call with no id to list all jobs.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| id | string | no | Job id returned by delegate with background:true. Omit to list all jobs |
Read the current forge-delegate configuration: defaultModel, defaultAgent, defaultVariant, autoApprove, timeoutMs, defaultDirectory, and named profiles — plus the installed version and whether it updates automatically. Call this to see what will be used when a model/directory is omitted, or when…
No parameter schema on file.
Change forge-delegate configuration at runtime — no reinstall. Only change settings when the user asks; never raise defaultModel to a premium tier on your own. Pass any subset of {defaultModel, defaultAgent, defaultVariant, autoApprove, timeoutMs, defaultDirectory, profiles}. Set a field to null…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| defaultModel | string | no | provider/model used when a call omits model |
| defaultAgent | string | no | opencode agent used when a call omits agent |
| defaultVariant | string | no | Reasoning-effort variant, sent to opencode as provider/model#variant |
| autoApprove | boolean | no | Let delegated agents edit files and run commands without asking |
| timeoutMs | number | no | Per-delegation timeout in milliseconds (default 900000, 15 minutes) |
| defaultDirectory | string | no | Absolute project path used when a call omits directory |
| profiles | object | no | The whole profiles object: { name: { model, agent, variant, autoApprove, directory } }. A profile set to null is deleted |
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 Forge Delegate 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: —
BTrust score 87 / 100
Release 1.2.4 · scanned 28 Oct 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 score94
Client score87
Findings6 threat · 0 capability
Capabilityhigh
Coveragesource
Verificationrepo
Surface digestf9f43e023ee729afbe70ce164ee2d8cf3e163cfec4c6966c67b2ef2b07c20c6e
Score vectorthreat 94 → client 87
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | high | capability blast radius (high) — client exposure if the model is manipulated | −6 |
| verification-discount | repo | publisher verification (public source) — no provenance, but the source is public and inspectable | −1 |
| 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 (6 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 |
|---|---|---|
| list_models | no tags | |
| ask_model | no tags | |
| delegate | no tags | |
| check_delegation | no tags | |
| get_delegate_config | no tags | |
| set_delegate_config | 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 digestf9f43e023ee729af
Scanned2026-10-28
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 1.2.4. Pin a release below and the command asks for exactly that one.
1.2.4
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 Forge Delegate 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.