AI Blocks
REMOTE · USEAIBLOCKS.COM
Search and load free AI skills, workflows, agents and prompts. Read-only, no sign-in.
Available components
Last scanned (22 hours ago)
Scores higher than 62% of remote servers
Reachable. Last reached 21 Nov 2026.
Category AI and Machine Learning
How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. How we score → Why this is hard to score →
Endpoint Security74
- The endpoint's TLS certificate is valid, in date, and uses a strong key. View diagnostics → Pass
- No authorisation is required to call this server. Nothing on it is marked destructive, but we can't show that an anonymous caller can only read: full credit needs the server to list at least one tool and every tool to be verifiably read-only. We use a best-effort check of tool names and descriptions to tell read-only tools from tools that change things, so some genuinely read-only tools may not get full credit. Names that start with a read verb (get, list, read, search and similar) and accurate readOnlyHint annotations help. Meet that to earn full credit, or require authorisation. See how to fix → View diagnostics → Partial
- HTTPS is enforced; there's no plaintext access path. View diagnostics → Pass
- HSTS check failed: the Strict-Transport-Security header is absent. See how to fix → View diagnostics → Fail
- DNSSEC check failed: this domain isn't protected by DNSSEC. See how to fix → View diagnostics → Fail
Transport & Reachability100
- Verified streamable-http transport via a live MCP handshake. View diagnostics → Pass
Schema Quality & AI Usability71
- 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).Pass
- AI-judged instruction clarity (good).Pass
- Context-footprint check failed: tool/resource definitions use about 4374 tokens (~182/item across 24 items; 22 tools + 2 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 Management42
- Stability check failed: schema churn in the 16 days we've observed: 2 tool removals, 0 breaking changes, 0 auth/transport breaks, 7 additions. See how to fix → Fail
Tool Coverage84
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 43% of tool parameters carry a description.Partial
- Structured output schemas are declared (95% of tools); any adoption earns full credit.Pass
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- We read all 22 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
- An AI judge read all 24 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
Checks we ran (13)
- TLS certificate
- Authorization
- HTTPS
- HSTS header
- DNSSEC
- Transport
- Schema quality
- Stability
- Tool coverage
- Injection markers
- Destructive annotations
- Judged manipulation
- MCP protocol
Does not apply to this hosted endpoint (2)
- Supply Chain SecurityScored on package channels only. This is a hosted endpoint, so there is nothing to install or inspect.
- Provenance & TransparencyScored on package channels only. This is a hosted endpoint, so there is nothing to install or inspect.
The score does not measure everything. What the score does not measure →
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.
- 21 Nov 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 38 to 42.
- 18 Nov 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 28 to 32.
- 16 Nov 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 22 to 25.
- 14 Nov 26 −1
- Stability: 0.27 → fail ▼ security
- Tool “get_skill” was removed ▼ security
- Tool “get_workflow” was removed ▼ security
- Tool “propose_team” was removed ▼ security
- The server rewrote its instructions, which are the text every model session reads security
- Tool “advance_job” rewrote its description, which is the text the model reads security
- Tool “advance_outcome” rewrote its description, which is the text the model reads security
- Tool “fetch” rewrote its description, which is the text the model reads security
- Tool “get_approaches” rewrote its description, which is the text the model reads security
- Tool “get_item” rewrote its description, which is the text the model reads security
- Tool “get_job_templates” rewrote its description, which is the text the model reads security
- Tool “get_resource” rewrote its description, which is the text the model reads security
- Tool “plan_workflow” rewrote its description, which is the text the model reads security
- Tool “prepare_job_context” rewrote its description, which is the text the model reads security
- Tool “prepare_workflow” rewrote its description, which is the text the model reads security
- Tool “read_back_outcome_experiment” rewrote its description, which is the text the model reads security
- Tool “search” rewrote its description, which is the text the model reads security
- Tool “search_library” rewrote its description, which is the text the model reads security
- Tool “start_job” rewrote its description, which is the text the model reads security
- Schema quality: 162 → 182 ▼ functional
- Server version: 3.0.0 → 3.1.0 functional
- “start_job” added an optional parameter “from_context” cosmetic
- “prepare_workflow” reworded the description of “user_inputs” cosmetic
- 13 Nov 26 +1
- The server rewrote its instructions, which are the text every model session reads security
- Tool “prepare_job_context” rewrote its description, which is the text the model reads security
- 11 Nov 26 +2
- The server rewrote its instructions, which are the text every model session reads security
- Tool “advance_job” rewrote its description, which is the text the model reads security
- Tool “get_job_templates” rewrote its description, which is the text the model reads security
- Tool “plan_workflow” rewrote its description, which is the text the model reads security
- Tool “prepare_job_context” rewrote its description, which is the text the model reads security
- Tool “propose_team” rewrote its description, which is the text the model reads security
- Tool “search_library” rewrote its description, which is the text the model reads security
- Tool “start_job” rewrote its description, which is the text the model reads security
- Tool “start_outcome” rewrote its description, which is the text the model reads security
- Destructive annotations: 0 → pass functional
- Tool “advance_job” changed its title: Validate the next job event → Check the next step of a team job cosmetic
- Tool “get_job_templates” changed its title: Read the job method and delivery templates → Read the team method and templates cosmetic
- Tool “prepare_job_context” changed its title: Ground a job before producing anything → Start any piece of work cosmetic
- Tool “propose_team” changed its title: Propose experts and a task lead → Preview a lead and helpers cosmetic
- Tool “start_job” changed its title: Scope a job and staff a flexible team → Name the lead for a job cosmetic
- Tool “start_outcome” changed its title: Start here for any business goal → Work on a business goal cosmetic
- 10 Nov 26 +1
- The server rewrote its instructions, which are the text every model session reads security
- Tool “advance_job” rewrote its description, which is the text the model reads security
- Tool “advance_outcome” rewrote its description, which is the text the model reads security
- Tool “propose_team” rewrote its description, which is the text the model reads security
- Tool “record_outcome_decision” rewrote its description, which is the text the model reads security
- Tool “record_outcome_experiment” rewrote its description, which is the text the model reads security
- Tool “start_outcome” rewrote its description, which is the text the model reads security
- Schema quality: 4078 → 4503 ▼ functional
- New tool “prepare_job_context” functional
- “start_job” added an optional parameter “deliverable_kind” cosmetic
- “start_job” added an optional parameter “has_existing_asset” cosmetic
- “start_job” added an optional parameter “site_url” cosmetic
- 9 Nov 26 −2
- Tool “advance_outcome” rewrote its description, which is the text the model reads security
- Tool “record_outcome_decision” rewrote its description, which is the text the model reads security
- Tool “record_outcome_experiment” rewrote its description, which is the text the model reads security
- Tool “start_outcome” rewrote its description, which is the text the model reads security
- Tool coverage: 61% → 42% ▼ functional
- Schema quality: 190 → 156 ▲ functional
- Destructive annotations: pass → 0 functional
- New tool “advance_job” functional
- New tool “get_approaches” functional
- New tool “get_job_preferences” functional
- New tool “get_job_templates” functional
- New tool “propose_team” functional
- New tool “set_job_preferences” functional
- New tool “start_job” functional
- “find_specialist” added an optional parameter “diverse” cosmetic
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 · Probed https://useaiblocks.com/mcp
TLS valid
Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .
| Subject | Issuer | Valid from | Valid until | Key | Signature | Serial |
|---|---|---|---|---|---|---|
| CN=useaiblocks.com | CN=WE1,O=Google Trust Services,C=US | 6 Nov 2026 | 4 Feb 2027 | ECDSA 256 | ECDSA-SHA256 | 1182712dfff494e70e90ba833fcebc42 |
| SANs: useaiblocks.com, agents.useaiblocks.com, *.agents.useaiblocks.com | ||||||
| CN=WE1,O=Google Trust Services,C=US (CA) | CN=GTS Root R4,O=Google Trust Services LLC,C=US | 13 Dec 2023 | 20 Feb 2029 | ECDSA 256 | ECDSA-SHA384 | 7ff31977972c224a76155d13b6d685e3 |
| CN=GTS Root R4,O=Google Trust Services LLC,C=US (CA) | CN=GlobalSign Root CA,OU=Root CA,O=GlobalSign nv-sa,C=BE | 15 Nov 2023 | 28 Jan 2028 | ECDSA 384 | SHA256-RSA | 7fe530bf331343bedd821610493d8a1b |
Background: What to check on a remote MCP endpoint →
DNSSEC insecure
Validation of useaiblocks.com. — Not signed
| Zone | DS | Keys | Algorithms | Outcome |
|---|---|---|---|---|
| . | Trust anchor | 20326, 38696 | 8, 8 | Verified |
| com. | DS published | 19718 | 13 | Verified |
| useaiblocks.com. | No DS | Unsigned (proven) parent-signed NSEC/NSEC3 proves an unsigned delegation |
Authentication No authorisation required
The endpoint answered without asking for a token. Anyone who knows the URL can reach it.
| Result | No authorisation required |
|---|---|
| HTTP status | 200 |
| Header | Value |
|---|---|
| x-content-type-options | nosniff |
Background: How OAuth 2.1 works in the 2026 MCP spec →
Transports 2 probes
| Transport | URL | Outcome | Status | Location |
|---|---|---|---|---|
| streamable-http | https://useaiblocks.com/mcp | Verified | 200 | |
| http (plaintext) | http://useaiblocks.com/mcp | HTTPS enforced | 301 | https://useaiblocks.com/mcp |
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 →
advance_job Check the next step of a team job ~172
For a team job from start_job only; an engagement from start_outcome moves with advance_outcome. Send the latest complete state and state_digest unchanged, with one event and its document. Each step checks its record; a refusal names the field to fix. Artifacts stay local; send hashes. This server keeps no copy, so there is no read or delete call: the state you hold is the record (read it from your local file; deleting that file ends the job). Every result is a host report, not proof of execution or consent.
| Name | Type | Req | Description |
|---|---|---|---|
| accept_proposal | boolean | – | – |
| document | object | yes | – |
| event | string | yes | – |
| job_id | string | yes | – |
| schema | string | – | – |
| state | object | yes | – |
| state_digest | string | yes | – |
| Name | Type | Req | Description |
|---|---|---|---|
| schema | string | yes | – |
No examples provided.
advance_outcome Move an outcome engagement forward ~257
For an engagement from start_outcome only; a team job from start_job moves with advance_job. Apply one event to an engagement. This server keeps no copy, so there is no read or delete call: engagement.json in outcomes/<id>/ is the record (read it there; deleting the folder ends the 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. Every problem in an event comes back at once, with its field path.
| Name | Type | Req | Description |
|---|---|---|---|
| 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. |
| Name | Type | Req | Description |
|---|---|---|---|
| schema | string | yes | – |
No examples provided.
fetch Fetch one item (deep research shape) ~103
Only for ChatGPT deep research and company knowledge: read one item by the id from search (such as skill/ad-angle-planner). Every other client: use get_item with the id from search_library. Returns 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.
| Name | Type | Req | Description |
|---|---|---|---|
| id | string | yes | An id from search. |
| Name | Type | Req | Description |
|---|---|---|---|
| id | string | yes | – |
| metadata | object | yes | – |
| text | string | yes | – |
| title | string | yes | – |
| url | string | yes | – |
No examples provided.
find_specialist Find a specialist for a task ~79
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.
| Name | Type | Req | Description |
|---|---|---|---|
| area | string | – | – |
| diverse | boolean | – | Re-rank candidates for distinct families and lenses. |
| limit | integer | – | – |
| task | string | yes | – |
| Name | Type | Req | Description |
|---|---|---|---|
| schema | string | yes | – |
No examples provided.
get_approaches See the distinct ways to do a job ~77
Use to compare the different ways a job can be done before choosing one: source-backed approach families, methods, lenses and needed tools. Not needed to do a job (start_job picks the approach). Coverage and review gaps are reported honestly. Pass job or task.
| Name | Type | Req | Description |
|---|---|---|---|
| job | string | – | – |
| task | string | – | – |
| Name | Type | Req | Description |
|---|---|---|---|
| schema | string | yes | – |
No examples provided.
get_item Get any item by id ~283
The one tool to read an item: any kind, by the id from a search_library or plan_workflow row (skill, workflow, agent, prompt, mind, AI tool or mini tool). Not for ChatGPT deep research, which reads search results with fetch. A skill comes with step_map (what goes before and after it); a workflow with its steps, handoff_check, a diagram to show and open_in_builder. 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 (SKILL.md, or a workflow's governing instructions and step notes) or the whole record; use it before running an item. Pin revision_sha256 to the revision you chose, read required files with get_resource, and cite its url.
| Name | Type | Req | Description |
|---|---|---|---|
| id | string | yes | The id from a search_library row. |
| response_format | string | – | 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. |
| revision_sha256 | string | – | Exact lowercase catalogue SHA-256 revision returned by discovery or retrieval. |
| type | string | – | The row's type. Needed only when two kinds share an id. |
| Name | Type | Req | Description |
|---|---|---|---|
| id | string | yes | – |
| next_action | string | – | – |
| one_line | string | yes | – |
| response_format | string | – | – |
| schema | string | yes | – |
| tested | boolean | yes | – |
| title | string | yes | – |
| type | string | yes | – |
| updated | string|null | – | – |
| url | string | yes | – |
No examples provided.
get_job_preferences Read saved job choices or local defaults ~47
On this anonymous service, return recommended choices and a local-file template. Signed-in connections use the scoped private preference record. No private data is loaded publicly.
| Name | Type | Req | Description |
|---|---|---|---|
| preferences | object | – | – |
| Name | Type | Req | Description |
|---|---|---|---|
| schema | string | yes | – |
No examples provided.
get_job_templates Read the team method and templates ~64
For team jobs: JOB-METHOD.md (the short team method), JOB-RECORDS.md (every record field; open it only when advance_job refuses a record) and the delivery templates.
| Name | Type | Req | Description |
|---|---|---|---|
| host_profile | string | – | – |
| tier | string | – | – |
| Name | Type | Req | Description |
|---|---|---|---|
| schema | string | yes | – |
No examples provided.
get_resource Retrieve a skill supporting resource ~137
Use after get_item to read one file from its file list (a script, template or reference), at that 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.
| Name | Type | Req | Description |
|---|---|---|---|
| limit | integer | – | – |
| offset | integer | – | Offset in Unicode code points, as returned by next_offset. |
| path | string | yes | – |
| revision_sha256 | string | yes | Exact lowercase catalogue SHA-256 revision returned by discovery or retrieval. |
| slug | string | yes | – |
No output schema declared.
No examples provided.
plan_workflow Plan a multi-step workflow ~389
Use when a multi-step job has no steps chosen yet: it finds candidate steps. Once you have step ids, in order, use prepare_workflow to check or change them; to read one ready workflow, use get_item. Results are suggestions, not a complete context-validated plan. Before calling, form a task brief from the current chat, supplied files and the user's me.md if they shared it: 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 notes and handoffs against that brief and prepare_workflow. Returns a diagram you can show the user. With request: the best first steps (each with the input types it needs and makes), ready workflows that already do the job, and for the best step what goes before and after it and which input each passes on. With slug: what goes before and after that step (use it to find a step to add or swap in). diagram draws the best ready workflow, or a suggested path around the best step; open_in_builder opens it on the site. Returns compact rows (id, type, title, url, one_line, tested); load full instructions only for the chosen ids with get_item, and cite their url. Plain code; does not use a server-side model.
| Name | Type | Req | Description |
|---|---|---|---|
| limit | integer | – | First steps for a request (default 5), or before and after steps for a slug (default 3). |
| request | string | – | What the user wants, in their words. Send request or slug, not both. |
| response_format | string | – | 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. |
| slug | string | – | One step to map before and after. |
| Name | Type | Req | Description |
|---|---|---|---|
| schema | string | yes | – |
No examples provided.
prepare_job_context Start any piece of work ~181
The first call for any named piece of work: a page, ad, email, copy, audit, analysis, plan or code. Then start_job. A goal with no deliverable named yet ("more sales") goes to start_outcome instead of both. Returns a short brief to act on, up to 3 questions to ask (each with a default) and whether one lead or a team fits. Also an annex to save: what to capture from the client’s real site or data, the rubric and gates, and the AI defaults to avoid. No model calls.
| Name | Type | Req | Description |
|---|---|---|---|
| category | string | – | – |
| deliverable_kind | string | – | Declare it; a word guess is only a suggestion. |
| has_existing_asset | boolean | – | true: patch an existing asset. |
| request | string | yes | – |
| site_url | string | – | – |
| Name | Type | Req | Description |
|---|---|---|---|
| schema | string | yes | – |
No examples provided.
prepare_outcome_pattern Prepare a plan pattern to share ~165
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.
| Name | Type | Req | Description |
|---|---|---|---|
| consent | object | – | – |
| engagement | object | yes | The complete engagement.json from the last outcome tool result, unchanged. |
| engagement_sha256 | string | yes | – |
| experiments | string | – | Optional text of experiments.jsonl, to include results as relative change. |
| keep | array | – | Public words to keep, such as a platform name. |
| remove | array | – | More words that identify the business. |
| Name | Type | Req | Description |
|---|---|---|---|
| schema | string | yes | – |
No examples provided.
prepare_specialist Load a base specialist or prepare a job ~171
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 no private files.
| Name | Type | Req | Description |
|---|---|---|---|
| context | string | – | – |
| deliverables | array | – | Actual task-specific files or outcomes. The host checks whether the worker covers them; source-method examples are not mandatory extra work. |
| me | string | – | – |
| role_id | string | – | – |
| task | string | – | – |
| tools | string | – | – |
| training | string | – | – |
| Name | Type | Req | Description |
|---|---|---|---|
| schema | string | yes | – |
No examples provided.
prepare_workflow Check, change and prepare a workflow ~494
Use when you already have the step ids, in order, and the user wants to see, check or change a workflow (swap, add, remove or reorder steps); also before showing any plan. No steps yet: use plan_workflow to find them. Quick check: send slugs, the step ids in order (from get_item 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 step or given by the user, plus swap_options for each step), suggestions with reasons (insert a step that makes a missing input, reorder by data flow, swap a step, remove a repeat), the proposed steps with all but swaps applied, and open_in_builder, a link that opens the proposal in the site's builder. Also returns an unsaved portable draft, selected skill inventory, review hash and handoff_check. Send full steps with pinned revisions instead of slugs for custom notes and dependencies. Suggestions and warnings never block the draft; show them and apply only what the user approves. Does not compose with our AI, save, execute or certify approval; an approval hash never authorizes external actions.
| Name | Type | Req | Description |
|---|---|---|---|
| approved_draft_hash | string | – | Optional host-reported hash of the exact previously reviewed draft. This field cannot establish consent or execution authorization. |
| custom_skills | array | – | – |
| goal | string | – | Optional. What the workflow is for. |
| governing_skills | array | – | – |
| name | string | – | Optional. Defaults to the goal. |
| notes | string | – | – |
| response_format | string | – | 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. |
| slugs | array | – | 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. |
| steps | array | – | Full step objects with pinned revisions, notes and dependencies. Send steps or slugs, not both. |
| user_inputs | array | – | Input types the user will give (such as ad_copy; get_item 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. |
| Name | Type | Req | Description |
|---|---|---|---|
| schema | string | yes | – |
No examples provided.
read_back_outcome_experiment Read back a running experiment ~184
Use while an experiment from record_outcome_experiment is live (that tool registers and closes it). 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. Budget and pause ideas come back as proposals for the owner; nothing is ever changed.
| Name | Type | Req | Description |
|---|---|---|---|
| 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 | – | – |
| schedule | object | – | – |
| Name | Type | Req | Description |
|---|---|---|---|
| schema | string | yes | – |
No examples provided.
record_outcome_decision Record the owner's decision ~132
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.
| Name | Type | Req | Description |
|---|---|---|---|
| decision | object | yes | considered is best-ranked first; passing over the top option needs a rationale. |
| 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. |
| Name | Type | Req | Description |
|---|---|---|---|
| schema | string | yes | – |
No examples provided.
record_outcome_experiment Register or close an experiment ~155
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.
| Name | Type | Req | Description |
|---|---|---|---|
| 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. |
| Name | Type | Req | Description |
|---|---|---|---|
| schema | string | yes | – |
No examples provided.
search Search (deep research shape) ~65
Only for ChatGPT deep research and company knowledge, which need this exact shape: results with id, title and url. Read one with fetch. Every other client: use search_library, the same search with filters and one-line summaries.
| Name | Type | Req | Description |
|---|---|---|---|
| query | string | yes | What to look for. |
| Name | Type | Req | Description |
|---|---|---|---|
| results | array | yes | – |
No examples provided.
search_library Find any AI Blocks item ~336
Use to browse or look up catalogue items by keywords, job or date. Not for doing a piece of work (prepare_job_context) or a business goal (start_outcome). The search tool is the same search in the shape only ChatGPT deep research needs; every other client uses this one. Finds skills, workflows, agents, prompts, minds, AI tools and mini tools. 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); read only the ones you choose with get_item, and cite their url. Plain search; does not use a server-side model.
| Name | Type | Req | Description |
|---|---|---|---|
| category | string | – | – |
| job | string | – | A job id such as make-image-ads (the resource aiblocks://jobs lists them; get_item shows an item's job). |
| level | string | – | – |
| limit | integer | – | – |
| offset | integer | – | – |
| query | string | – | Keywords or the user's words. Leave it out to browse with job or since. |
| response_format | string | – | concise (default): compact rows. detailed: also inputs, outputs, revision, source and dates. |
| since | string | – | ISO date. Only items added or changed on or after it; newest first when there is no query. |
| tested | boolean | – | true: only items with the Safety checked label (safety scan passed and a clear list of what goes in and comes out). |
| type | string | – | Only this kind of item. |
| Name | Type | Req | Description |
|---|---|---|---|
| filters | object | – | – |
| items | array | yes | – |
| next_offset | integer|null | yes | – |
| notice | string | – | – |
| offset | integer | yes | – |
| query | string | – | – |
| schema | string | yes | – |
| total | integer | yes | – |
No examples provided.
set_job_preferences Prepare local saved job choices ~72
Anonymous calls only prepare local preference files; they save nothing on the server. Signed-in connections require the selected workspace write consent. An ordinary one-off request never changes saved defaults.
| Name | Type | Req | Description |
|---|---|---|---|
| answers | object | yes | – |
| job | string | – | – |
| preferences | object | – | – |
| request | string | – | – |
| Name | Type | Req | Description |
|---|---|---|---|
| schema | string | yes | – |
No examples provided.
start_job Name the lead for a job ~314
Use after prepare_job_context (send from_context: true so the brief is not repeated); not for a goal with no deliverable (start_outcome). Decides who does a job and says why. One kind of work: one lead, with the lead to load, the questions and the rubric. Mixed kinds of work, a large batch or mode team: one lead with helpers, the short team method and a state for advance_job. All work runs in the user’s AI; no server model calls or action authority.
| Name | Type | Req | Description |
|---|---|---|---|
| context_refs | array | – | – |
| deliverable_kind | string | – | Declare it; a word guess is only a suggestion. |
| dials | object | – | – |
| from_context | boolean | – | true: the prepare_job_context result is already in hand, so start_job omits its brief, questions and rubric. |
| from_option | string | – | – |
| has_existing_asset | boolean | – | true: patch an existing asset. |
| host_capabilities | object | – | – |
| host_profile | string | – | – |
| item_id | string | – | – |
| job | string | – | – |
| job_reason | string | – | – |
| mode | string | – | – |
| option_source | object | – | – |
| parent_outcome_id | string | – | – |
| persona_id | string | – | – |
| preferences | object | – | – |
| preferences_ref | object | – | – |
| request | string | yes | – |
| role_id | string | – | – |
| site_url | string | – | – |
| Name | Type | Req | Description |
|---|---|---|---|
| schema | string | yes | – |
No examples provided.
start_outcome Work on a business goal ~175
For a goal or problem with no deliverable named yet, in the owner's own words ("more customers", "my ad costs are rising"). For a named piece of work, such as a page, ads, emails, an audit or a plan, use prepare_job_context. 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.
| Name | Type | Req | Description |
|---|---|---|---|
| engagement_id | string | – | – |
| include_example | boolean | – | Add the worked example (rising ad costs) to see the quality bar. Off by default; it is large. |
| request | string | yes | – |
| started | string | – | – |
| Name | Type | Req | Description |
|---|---|---|---|
| schema | string | yes | – |
No examples provided.
How do I install the AI Blocks MCP server?
AI Blocks is a hosted endpoint at https://useaiblocks.com/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
remote · useaiblocks.com
claude mcp add --transport http com-useaiblocks-library 'https://useaiblocks.com/mcp'
What is the AI Blocks MCP server?
AI Blocks is an MCP server listed in the public MCP registry as com.useaiblocks/library. Search and load free AI skills, workflows, agents and prompts. Read-only, no sign-in. This page covers its hosted endpoint (https://useaiblocks.com/mcp).
Is the AI Blocks MCP server safe to use?
AI Blocks scores 75 out of 100 on VerifyMCP. 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 AI Blocks MCP server expose?
AI Blocks exposes 22 tools: start_outcome, advance_outcome, record_outcome_decision, record_outcome_experiment, read_back_outcome_experiment, and 17 more. Their descriptions and schemas cost roughly 4,052 tokens of context every time the server is loaded.
Does the AI Blocks MCP server require authentication?
No. We connected to AI Blocks without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.
Is the AI Blocks MCP server still maintained?
AI Blocks 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 did VerifyMCP test on the AI Blocks MCP server?
VerifyMCP ran 13 checks on AI Blocks, covering TLS certificate, Authorization, HTTPS, HSTS header and 9 more. Supply Chain Security and Provenance & Transparency do not apply to a hosted endpoint, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.