MCP Server for Z.AI - A Model Context Protocol server that provides AI capabilities
Nothing to run from here
AI Blocks 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.
96/100
tool-list score
17
tools declared
remote
at its publisher
—
calls last 7d
What it does
Search and load free AI skills, workflows, agents and prompts. Read-only, no sign-in.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user --transport http ai-blocks-mcp https://useaiblocks.com/mcp
# 2 — ask your agent for something these tools do
# start_outcome, advance_outcome, record_outcome_decision and 14 more
AI Blocks costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Publishernot claimed
USAll 1 server
useaiblocks1 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. Nothing here runs on your machine and nothing runs on ours: this server answers at its publisher’s own address, and what you install is the connection straight to it.
Claude Codedeclared by this listing
This is a public server: it answers at its publisher’s own address and this marketplace is not in the path. Claude Code registers it in one command; --scope user makes it available in every project. The transport below is http, as the publisher's own manifest declares it.
claude mcp add --scope user --transport http ai-blocks-mcp https://useaiblocks.com/mcpReconnect, or start a new session, and the tools appear in the model’s tool list.
Free on mcprush, and it answers at its publisher’s own address: 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 pointing straight at the publisher’s own address — this marketplace is not in the path, and nothing from this listing executes on your machine.
What you approve
17 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.
The front door for any goal or problem the owner states, in their own words. Returns a new engagement waiting for its brief, the next step and the files for outcomes/<id>/, with METHOD.md (brief frame with examples, research protocol, composition and run rules). include_example adds a worked example of a good brief, research and plan. No work runs here.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| request | string | yes | — |
| engagement_id | string | no | — |
| started | string | no | — |
| include_example | boolean | no | Add the worked example (rising ad costs) to see the quality bar. Off by default; it is large. |
Apply one event to an engagement. Before the run: brief (the pinned-down outcome), plan (research and the composed plan, checked against our rules and the live catalogue), approve_plan (owner only). During the run: data, start, complete (with outputs and checks), approve (owner only), skip, block, reopen, next_round; a plan event during the run is a revision. autonomy (owner only) works any time.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| engagement | object | yes | The complete engagement.json from the last outcome tool result, unchanged. |
| engagement_sha256 | string | yes | engagement_sha256 from the last outcome tool result. A different value means the engagement changed. |
| event | yes | One event. type picks the fields: brief, plan (research + plan), approve_plan, data, start, complete, approve, skip, block, reopen, autonomy, next_round. |
Record what the owner chose, the options considered (best-ranked first), what they passed over and why. Passing over the top option needs a reason. Returns a line for decisions.jsonl and, if a durable rule was stated, a learning candidate with where to save it.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| engagement | object | yes | The complete engagement.json from the last outcome tool result, unchanged. |
| engagement_sha256 | string | yes | engagement_sha256 from the last outcome tool result. A different value means the engagement changed. |
| decision | object | yes | considered is best-ranked first; passing over the top option needs a rationale. |
Register a test before it goes live (action register: change, metric, baseline, window, minimum volume, guardrails), then close it (action close: observed, volume, guardrail results, verdict). Low volume forces INCONCLUSIVE; a broken guardrail is never a WIN. Returns a line for experiments.jsonl, a learning candidate and an anonymised outcome report the owner may choose to share.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| engagement | object | yes | The complete engagement.json from the last outcome tool result, unchanged. |
| engagement_sha256 | string | yes | engagement_sha256 from the last outcome tool result. A different value means the engagement changed. |
| experiment | yes | register before the change goes live; close with what was observed. |
Without a reading: the read-back schedule for every open experiment and a routine prompt for a host scheduler (Claude Code scheduled task or cron), set up only if the owner agrees. With a reading: compares it with the registered baseline, minimum volume and guardrails; flags a guardrail breach at once; after the window, returns an honest verdict and the close payload for record_outcome_experiment.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| engagement | object | yes | The complete engagement.json from the last outcome tool result, unchanged. |
| engagement_sha256 | string | yes | — |
| experiments | string | yes | The text of experiments.jsonl. |
| reading | object | no | — |
| schedule | object | no | — |
After a finished round, returns the exact anonymised PATTERN.json the owner would share (names, figures, links and contact details removed) and its sha256. Only if the owner says yes to that file, call again with consent to get PATTERN-SUBMISSION.json for review by a person at AI Blocks. Nothing is sent or published.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| engagement | object | yes | The complete engagement.json from the last outcome tool result, unchanged. |
| engagement_sha256 | string | yes | — |
| experiments | string | no | Optional text of experiments.jsonl, to include results as relative change. |
| remove | array | no | More words that identify the business. |
| keep | array | no | Public words to keep, such as a platform name. |
| consent | object | no | — |
Find worker candidates for a deliverable. Compare their remit and outputs, then use prepare_specialist to onboard the chosen worker. Keep unrelated private context out of discovery.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| task | string | yes | — |
| area | string | no | — |
| limit | integer | no | — |
Supply role_id only to load a complete base specialist: README, setup, SOUL, intake, playbook, handoff and best-practice files, pinned methods and a full ZIP download. The host AI asks task and output questions in the conversation; no website context form is required. Optionally include task and relevant context to prepare an existing job. This service makes no model calls, runs no work and stores
| Parameter | Type | Required | Notes |
|---|---|---|---|
| role_id | string | no | — |
| task | string | no | — |
| context | string | no | — |
| tools | string | no | — |
| training | string | no | — |
| me | string | no | — |
| deliverables | array | no | Actual task-specific files or outcomes. The host checks whether the worker covers them; source-method examples are not mandatory extra work. |
Find one item for a task (for a whole business goal, use start_outcome). Find skills, workflows, agents, prompts, minds, AI tools and mini tools by keywords and intent. Filters: type, job, level, tested, since (what's new). With no query, a job or since browses. Returns compact rows (id, type, title, url, one_line, tested); load only the ones you choose with get_skill, get_workflow or get_item, an
| Parameter | Type | Required | Notes |
|---|---|---|---|
| query | string | no | Keywords or the user's words. Leave it out to browse with job or since. |
| type | string | no | Only this kind of item. |
| job | string | no | A job id such as make-image-ads (the resource aiblocks://jobs lists them; get_item shows an item's job). |
| level | string | no | — |
| tested | boolean | no | true: only items with the Safety checked label (safety scan passed and a clear list of what goes in and comes out). |
| since | string | no | ISO date. Only items added or changed on or after it; newest first when there is no query. |
| category | string | no | — |
| limit | integer | no | — |
| offset | integer | no | — |
| response_format | string | no | concise (default): compact rows. detailed: also inputs, outputs, revision, source and dates. |
Find candidate steps for a multi-step job; these are suggestions, not a complete context-validated plan. First use the current chat, supplied files and authorized me.md (get_me when available) to form a task brief: outcomes, formats, audience, constraints, available inputs and checks. Keep private context in the host; send focused task terms here. Load chosen methods and resources, then compose no
| Parameter | Type | Required | Notes |
|---|---|---|---|
| request | string | no | What the user wants, in their words. Send request or slug, not both. |
| slug | string | no | One step to map before and after. |
| limit | integer | no | First steps for a request (default 5), or before and after steps for a slug (default 3). |
| response_format | string | no | concise (default): 3 steps before and after the best first step. detailed: 5, plus the optional inputs of each step and why it was picked. |
Retrieve a skill. Concise (default): summary, inputs, outputs, how to use, file list with hashes, and step_map (what usually goes before and after it and the input each passes on). response_format detailed adds the full SKILL.md instructions and resource links; use it before running the skill. Pin revision_sha256 to the selected catalogue revision. Fetch every required supporting resource before u
| Parameter | Type | Required | Notes |
|---|---|---|---|
| slug | string | yes | — |
| revision_sha256 | string | no | Exact lowercase catalogue SHA-256 revision returned by discovery or retrieval. |
| response_format | string | no | concise (default): a short view without the full instructions. detailed: everything, with the full SKILL.md text; use it only for an item you will run. |
Retrieve a public workflow, its declared order and skill references, plus handoff_check: which step passes each input to which, and which inputs the user gives. Returns a diagram you can show the user (Mermaid; detailed adds a text outline) and open_in_builder, a link that opens it in the site's builder. To change it, call prepare_workflow with the edited step ids as slugs. Concise (default) leave
| Parameter | Type | Required | Notes |
|---|---|---|---|
| slug | string | yes | — |
| revision_sha256 | string | no | Exact lowercase catalogue SHA-256 revision returned by discovery or retrieval. |
| response_format | string | no | concise (default): a short view without the full instructions. detailed: everything, with the full SKILL.md text; use it only for an item you will run. |
Read one inventoried resource at an exact skill revision. Text returns bounded ordered chunks; follow next_offset until null and verify full character coverage. Binary files return a download descriptor for the host to retrieve and verify. Paths are archive-relative, never arbitrary URLs or filesystem paths.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| slug | string | yes | — |
| path | string | yes | — |
| revision_sha256 | string | yes | Exact lowercase catalogue SHA-256 revision returned by discovery or retrieval. |
| offset | integer | no | Offset in Unicode code points, as returned by next_offset. |
| limit | integer | no | — |
Check a workflow, or a change to one. Call it whenever the user wants to see, check or change a workflow (swap, add, remove or reorder steps), and before showing any plan. Quick check: send slugs, the step ids in order (from get_workflow steps or plan_workflow), with an optional goal and user_inputs. Returns a diagram you can show the user, step_checks (is each required input made by an earlier st
| Parameter | Type | Required | Notes |
|---|---|---|---|
| name | string | no | Optional. Defaults to the goal. |
| goal | string | no | Optional. What the workflow is for. |
| notes | string | no | — |
| slugs | array | no | Step ids in order, for a quick check or a change: each pinned to its current revision and run after the one before. Send slugs or steps, not both. |
| response_format | string | no | concise (default): the Mermaid diagram and 2 swap options per step. detailed: also a text outline, the proposed workflow's diagram and 4 swap options per step. |
| steps | array | no | Full step objects with pinned revisions, notes and dependencies. Send steps or slugs, not both. |
| governing_skills | array | no | — |
| user_inputs | array | no | Input types the user will give (such as ad_copy; get_workflow lists a workflow's in handoff_check.user_inputs). The hand-off check treats them as supplied; they are not part of the draft hash. |
| custom_skills | array | no | — |
| approved_draft_hash | string | no | Optional host-reported hash of the exact previously reviewed draft. This field cannot establish consent or execution authorization. |
Get one item of any kind by the id from search_library: an agent, prompt, mind, AI tool or mini tool (skills and workflows work too). Concise (default): what it does, inputs and outputs, how to use it, files or links, and for AI tools the price, limits and when we last checked. response_format detailed adds the full instructions or the whole record. Cite its url.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| id | string | yes | The id from a search_library row. |
| type | string | no | The row's type. Needed only when two kinds share an id. |
| revision_sha256 | string | no | Exact lowercase catalogue SHA-256 revision returned by discovery or retrieval. |
| response_format | string | no | concise (default): a short view without the full instructions. detailed: everything, with the full SKILL.md text; use it only for an item you will run. |
Search AI Blocks in the shape ChatGPT deep research and company knowledge use: results with id, title and url. Read one with fetch. search_library does the same with filters and one-line summaries.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| query | string | yes | What to look for. |
Read one item by the id from search (such as skill/ad-angle-planner): its full text (the SKILL.md, or the AI tool or mini tool record), url to cite and metadata. Text over 48,000 characters is cut; metadata.rest says how to read the rest.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| id | string | yes | An id from search. |
Free
$0 forever
- Every tool — any call limit is its publisher’s, not ours
- No card, and mcprush charges nothing for it
- Runs at its publisher’s own address — this marketplace is not in the path
- 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 AI Blocks 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: —
ATool-list grade · score 96 / 100
Release 3.0.0 · scanned 6 Nov 2026
Graded from the tools this server lists, not from its source code.
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 score96
Findings0 threat · 0 capability
Capabilityminimal
Coveragemanifest
Verificationnot in this report
Surface digestc1a0dea01dbeebfad2e0d95c1b6eb3248ecc5070450a5e2a9f1678241d04df50
Score vectorthreat 100 → client 96
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | minimal | capability blast radius (minimal) — client exposure if the model is manipulated | −0 |
| coverage-honesty | manifest | inspection depth (manifest) — how much of the target the scan could see | −4 |
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.
The scan read each tool’s name, description, input schema and annotations exactly as the server listed them the last time it answered us; no code was reviewed. We ask the server again about once a month, and a list that changed is graded again.
Tool surfaceread
Implementation sourcenot available
Package metadatanot available
Live transportnot available
The implementation source was not read — this reflects the declared tool metadata only.
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. minimal is the level these add up to.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| start_outcome | no tags | |
| advance_outcome | no tags | |
| record_outcome_decision | no tags | |
| record_outcome_experiment | no tags | |
| read_back_outcome_experiment | no tags | |
| prepare_outcome_pattern | no tags | |
| find_specialist | no tags | |
| prepare_specialist | untrusted-input | untrusted-input: keyword "download" |
| search_library | no tags | |
| plan_workflow | no tags | |
| get_skill | untrusted-input | untrusted-input: keyword "fetch" |
| get_workflow | no tags | |
| get_resource | untrusted-input | untrusted-input: keyword "download" |
| prepare_workflow | no tags | |
| get_item | no tags | |
| search | untrusted-input | untrusted-input: keyword "fetch" |
| fetch | untrusted-input | untrusted-input: keyword "fetch" |
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 digestc1a0dea01dbeebfa
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
This is an address its publisher runs: which release it serves is theirs to choose, so there is nothing here to pin. The history below is for reading; the current release on file is 3.0.0.
3.0.0
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 AI Blocks 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.