StewAI
REMOTE · API.STEWAI.COM
Discover, run, inspect, build, test, and privately reuse AI workflows.
Available components
Last scanned (18 hours ago)
Scores higher than 52% 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 Security63
- The endpoint's TLS certificate is valid, in date, and uses a strong key. View diagnostics → Pass
- Authorisation check failed: no authorisation is required to call this server, and it exposes a tool marked destructive (cancel_recipe_activity). See how to fix → View diagnostics → Fail
- HTTPS is enforced; there's no plaintext access path. View diagnostics → Pass
- The HSTS (Strict-Transport-Security) header is present. View diagnostics → Pass
- 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 Usability34
- 0% of prompts and resources have a non-trivial description (not blank, and not just the item's name).Fail
- AI-judged instruction clarity (fair).Partial
- Tool/resource definitions use about 3227 tokens (~48/item across 67 items; 59 tools + 8 resources), lean.Pass
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management79
- Stability check failed: schema churn in the 30 days we've observed: 0 tool removals, 6 breaking changes, 0 auth/transport breaks, 45 additions. See how to fix → Fail
Tool Coverage73
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 5% of tool parameters carry a description.Partial
- Structured output schemas are declared (100% 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 59 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
- An AI judge read all 61 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
- Implements a current MCP spec version (2026-07-28).Pass
- Supports UI / widget rendering.Pass
Checks we ran (14)
- TLS certificate
- Authorization
- HTTPS
- HSTS header
- DNSSEC
- Transport
- Schema quality
- Stability
- Tool coverage
- Injection markers
- Destructive annotations
- Judged manipulation
- MCP protocol
- Capabilities
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.
- 18 Nov 26 −4
- Stability: pass → fail ▼ security
- New tool “cancel_recipe_activity”, which the server declares destructive security
- New tool “commit_recipe_acceptance_upload”, which the server declares destructive security
- New tool “commit_recipe_research_upload”, which the server declares destructive security
- New tool “commit_recipe_spec_upload”, which the server declares destructive security
- New tool “record_recipe_research”, which the server declares destructive security
- New tool “restore_recipe_build”, which the server declares destructive security
- New tool “resume_recipe_activity”, which the server declares destructive security
- New tool “set_recipe_acceptance_cases”, which the server declares destructive security
- New tool “set_recipe_contracts”, which the server declares destructive security
- New tool “set_recipe_metadata”, which the server declares destructive security
- Tool “check_recipe_build” rewrote its description, which is the text the model reads security
- Tool “commit_recipe_build” rewrote its description, which is the text the model reads security
- Tool “get_recipe_build” rewrote its description, which is the text the model reads security
- Tool “get_recipe_build_activity” rewrote its description, which is the text the model reads security
- Tool “get_recipe_preview” rewrote its description, which is the text the model reads security
- Tool “get_results” rewrote its description, which is the text the model reads security
- Tool “get_run” rewrote its description, which is the text the model reads security
- Tool “review_recipe_build” rewrote its description, which is the text the model reads security
- Tool “run_recipe” rewrote its description, which is the text the model reads security
- Tool “run_recipe_acceptance” rewrote its description, which is the text the model reads security
- Tool “update_recipe_build” rewrote its description, which is the text the model reads security
- Tool “review_recipe_build” is now declared destructive security
- Tool “run_recipe_acceptance” is now declared destructive security
- Tool coverage: 13% → 5% ▼ functional
- “update_recipe_build” added a required parameter “spec”, so existing callers break ▼ functional
- “commit_recipe_build” made “commit_capability” required, so existing callers break ▼ functional
- “get_recipe_build” made “build_ref” required, so existing callers break ▼ functional
- “get_run” made “run_id” required, so existing callers break ▼ functional
- “commit_recipe_build” dropped the required parameter “mode” ▼ functional
- “review_recipe_build” dropped the required parameter “mode” ▼ functional
- “run_recipe_acceptance” dropped the required parameter “mode” ▼ functional
- “update_recipe_build” dropped the required parameter “ops” ▼ functional
- Schema quality: fail → pass ▲ functional
- Schema quality: good → fair functional
- Server version: 0.3.186 → 0.3.187 functional
- New tool “append_recipe_build_upload” functional
- New tool “approve_recipe_budget” functional
- New tool “begin_recipe_build_upload” functional
- New tool “bind_recipe_resource” functional
- New tool “estimate_recipe_run” functional
- New tool “get_recipe_acceptance_plan” functional
- New tool “get_recipe_activity_billing” functional
- New tool “get_recipe_activity_coverage” functional
- New tool “get_recipe_authoring_guidance” functional
- New tool “get_recipe_build_contracts” functional
- New tool “get_recipe_build_node” functional
- New tool “get_recipe_build_research” functional
- New tool “get_recipe_build_schemas” functional
- New tool “get_recipe_capability” functional
- New tool “get_recipe_details” functional
- New tool “get_recipe_model” functional
- New tool “get_run_diagnostics” functional
- New tool “get_run_step” functional
- New tool “get_run_step_chunk” functional
- New tool “list_recipe_activity_assertions” functional
- New tool “list_recipe_activity_nodes” functional
- New tool “list_recipe_build_activities” functional
- New tool “list_recipe_build_capabilities” functional
- New tool “list_recipe_build_handoffs” functional
- New tool “list_recipe_build_nodes” functional
- New tool “list_recipe_build_resources” functional
- New tool “list_recipe_builds” functional
- New tool “list_recipe_capability_types” functional
- New tool “list_recipe_models” functional
- New tool “list_run_steps” functional
- New tool “list_runs” functional
- New tool “preflight_recipe_build” functional
- New tool “quote_recipe_acceptance” functional
- New tool “quote_recipe_review” functional
- New tool “render_recipe_build” functional
- “run_recipe_acceptance” reworded the description of “case_ids” cosmetic
- “check_recipe_build” dropped the optional parameter “render_only” cosmetic
- “get_recipe_build” dropped the optional parameter “cursor” cosmetic
- “get_recipe_build” dropped the optional parameter “include_archived” cosmetic
- “get_recipe_build” dropped the optional parameter “limit” cosmetic
- “get_recipe_build” dropped the optional parameter “model_id” cosmetic
- “get_recipe_build” dropped the optional parameter “node_id” cosmetic
- “get_recipe_build” dropped the optional parameter “node_type” cosmetic
- “get_recipe_build” dropped the optional parameter “schema_name” cosmetic
- “get_recipe_build” dropped the optional parameter “view” cosmetic
- “get_recipe_build_activity” dropped the optional parameter “section” cosmetic
- “get_recipe_preview” dropped the optional parameter “cursor” cosmetic
- “get_recipe_preview” dropped the optional parameter “view” cosmetic
- “get_results” dropped the optional parameter “chunk_ref” cosmetic
- “get_results” dropped the optional parameter “cursor” cosmetic
- “get_results” dropped the optional parameter “detail” cosmetic
- “get_results” dropped the optional parameter “limit” cosmetic
- “get_results” dropped the optional parameter “step_id” cosmetic
- “get_results” dropped the optional parameter “view” cosmetic
- “get_run” dropped the optional parameter “cursor” cosmetic
- “get_run” dropped the optional parameter “limit” cosmetic
- “get_run” dropped the optional parameter “recipe_ref” cosmetic
- “get_run” dropped the optional parameter “status” cosmetic
- “get_run” dropped the optional parameter “view” cosmetic
- “run_recipe” dropped the optional parameter “dry_run” cosmetic
- Tool “commit_recipe_build” changed its title: Commit a StewAI Recipe Build → Commit a Recipe Build cosmetic
- Tool “get_recipe_build” changed its title: Inspect a StewAI Recipe Build → Read a StewAI Recipe Build Summary cosmetic
- Tool “get_recipe_build_activity” changed its title: Get recipe build activity → Get Recipe Build Activity cosmetic
- Tool “get_results” changed its title: Get StewAI Run Results → Get StewAI Run Outputs cosmetic
- Tool “review_recipe_build” changed its title: Review recipe build → Review a Recipe Build cosmetic
- Tool “run_recipe_acceptance” changed its title: Run recipe acceptance → Run Recipe Acceptance cosmetic
- Tool “update_recipe_build” changed its title: Update a StewAI Recipe Build → Replace a Recipe Build Specification cosmetic
- 11 Nov 26 0
- Stability: 0.97 → pass security
- Server version: 0.3.185 → 0.3.186 functional
- 10 Nov 26 0
- Stability: pass → 0.97 functional
- 9 Nov 26 0
- Server version: 0.3.183 → 0.3.185 functional
- 8 Nov 26 0
- Server version: 0.3.182 → 0.3.183 functional
- 7 Nov 26 0
- Server version: 0.3.181 → 0.3.182 functional
- 6 Nov 26 0
- We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
- 5 Nov 26 0
- Server version: 0.3.179 → 0.3.181 functional
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://api.stewai.com/mcp
TLS valid
Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .
| Subject | Issuer | Valid from | Valid until | Key | Signature | Serial |
|---|---|---|---|---|---|---|
| CN=api.stewai.com | CN=WE1,O=Google Trust Services,C=US | 2 Oct 2026 | 31 Dec 2026 | ECDSA 256 | ECDSA-SHA256 | b4c1bbb0f0fb69950e05cea6fe4a64ab |
| SANs: api.stewai.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 api.stewai.com. — Not signed
| Zone | DS | Keys | Algorithms | Outcome |
|---|---|---|---|---|
| . | Trust anchor | 20326, 38696 | 8, 8 | Verified |
| com. | DS published | 19718 | 13 | Verified |
| stewai.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 |
|---|---|
| strict-transport-security | max-age=31536000; includeSubDomains |
| content-security-policy | default-src 'self'; script-src 'self' https://www.googletagmanager.com https://www.clarity.ms; style-src 'self' 'unsafe-inline'; img-src 'self' data: https://api.stewai.com https://www.google-analytics.com; font-src 'self' data:; connect-src 'self' https://api.stewai.com https://stewai.com wss://api.stewai.com wss://stewai.com https://www.google-analytics.com https://region1.google-analytics.com https://www.clarity.ms; frame-src 'self' https://www.youtube-nocookie.com; frame-ancestors 'none'; base-uri 'self'; form-action 'self' |
| x-content-type-options | nosniff |
| x-frame-options | SAMEORIGIN |
| referrer-policy | strict-origin-when-cross-origin |
| permissions-policy | geolocation=(), microphone=(), camera=() |
Background: How OAuth 2.1 works in the 2026 MCP spec →
Transports 2 probes
| Transport | URL | Outcome | Status | Location |
|---|---|---|---|---|
| streamable-http | https://api.stewai.com/mcp | Verified | 200 | |
| http (plaintext) | http://api.stewai.com/mcp | HTTPS enforced | 301 | https://api.stewai.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 →
review_recipe_build Review a Recipe Build ~47
Start one bounded semantic quality review of an exact private build revision.
| Name | Type | Req | Description |
|---|---|---|---|
| build_ref | string | yes | – |
| idempotency_key | string | yes | – |
| revision | string | yes | – |
Structured output declared, but exposes no named fields.
No examples provided.
run_recipe Run a StewAI Recipe ~74
Start one previewed public or account-authorized recipe exactly once. This spends credits and may call external providers. Use a fresh idempotency key for a new run; replay the same key after uncertainty.
| Name | Type | Req | Description |
|---|---|---|---|
| idempotency_key | string | yes | – |
| inputs | object | yes | – |
| recipe_ref | string | yes | – |
Structured output declared, but exposes no named fields.
No examples provided.
run_recipe_acceptance Run Recipe Acceptance ~75
Run selected behavioral acceptance cases, or the complete suite when case_ids is omitted, for one exact private build revision. This may spend credits and call external providers.
| Name | Type | Req | Description |
|---|---|---|---|
| build_ref | string | yes | – |
| case_ids | array | – | – |
| idempotency_key | string | yes | – |
| revision | string | yes | – |
Structured output declared, but exposes no named fields.
No examples provided.
search_recipes Search StewAI Recipes ~259
Find safe public recipes and published recipes available to the current account. results are direct fits (exact or strong); related_results are adjacent recipes, not direct fits. Each row states its output contract, past-run cost history and, for reviewed public recipes, that safety review is not output-quality validation. required_inputs and required_outputs match exact handles or normalized labels, never meanings. When paging.has_more is true, repeat the identical call with cursor=next_cursor.
| Name | Type | Req | Description |
|---|---|---|---|
| cursor | string | – | next_cursor from the previous page of the identical query and filters. Omit for the first page. |
| query | string | yes | At least 3 non-padding characters, up to 2000. Name the task in a few words; add constraints as required_inputs or required_outputs; follow next_cursor when results are cut. |
| required_inputs | array | – | Exact normalized handle/label matching, not semantic meaning; inspect filter_diagnostics for available labels. |
| required_outputs | array | – | Exact normalized handle/label matching, not semantic meaning; filters are never weakened automatically. |
| runnable_only | boolean | – | – |
| sources | array | – | When omitted, search public recipes and any library lanes authorized by this connection. Explicit private lanes require recipes:read permission. |
Structured output declared, but exposes no named fields.
No examples provided.
set_recipe_acceptance_cases Set Recipe Acceptance Cases ~54
Replace the complete behavioral acceptance suite of one private build.
| Name | Type | Req | Description |
|---|---|---|---|
| build_ref | string | yes | – |
| idempotency_key | string | yes | – |
| revision | string | yes | – |
| suite | object | yes | – |
Structured output declared, but exposes no named fields.
No examples provided.
set_recipe_contracts Set Recipe Build Contracts ~63
Replace the declared input and output contracts of one private build.
| Name | Type | Req | Description |
|---|---|---|---|
| build_ref | string | yes | – |
| idempotency_key | string | yes | – |
| input_contract | object | yes | – |
| output_contract | object | yes | – |
| revision | string | yes | – |
Structured output declared, but exposes no named fields.
No examples provided.
set_recipe_metadata Set Recipe Build Metadata ~57
Replace selected name, description, UI, or comment metadata on one private build.
| Name | Type | Req | Description |
|---|---|---|---|
| build_ref | string | yes | – |
| idempotency_key | string | yes | – |
| metadata | object | yes | – |
| revision | string | yes | – |
Structured output declared, but exposes no named fields.
No examples provided.
start_recipe_build Start a StewAI Recipe Build ~194
Create a private recipe build from a bounded intent and declared contract. Recipe inputs are strings: use type:string, positive maxLength, and only minLength:1 on required inputs. Richer input constraints must be handled in recipe logic and tested, not claimed as enforced by the input node. The response returns the stored contracts when they fit the bounded result; the archetype bundle is optional guidance, not the build contract. Optionally provide source_recipe_ref to adapt an owned recipe or a fully viewable public-open recipe into a new private draft.
| Name | Type | Req | Description |
|---|---|---|---|
| capabilities | array | yes | – |
| idempotency_key | string | yes | – |
| input_contract | object | yes | – |
| intent | string | yes | – |
| name | string | yes | – |
| output_contract | object | yes | – |
| quality_profile | – | yes | – |
| research_policy | – | yes | – |
| risk_domains | array | yes | – |
| source_recipe_ref | string | – | – |
Structured output declared, but exposes no named fields.
No examples provided.
update_recipe_build Replace a Recipe Build Specification ~64
Replace the complete executable specification of one private recipe build at an exact revision. This overwrites the prior draft specification.
| Name | Type | Req | Description |
|---|---|---|---|
| build_ref | string | yes | – |
| idempotency_key | string | yes | – |
| revision | string | yes | – |
| spec | object | yes | – |
Structured output declared, but exposes no named fields.
No examples provided.
How do I install the StewAI MCP server?
StewAI is a hosted endpoint at https://api.stewai.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 · api.stewai.com
claude mcp add --transport http com-stewai-stewai 'https://api.stewai.com/mcp'
What is the StewAI MCP server?
StewAI is an MCP server listed in the public MCP registry as com.stewai/stewai. Discover, run, inspect, build, test, and privately reuse AI workflows. This page covers its hosted endpoint (https://api.stewai.com/mcp).
Is the StewAI MCP server safe to use?
StewAI scores 68 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 StewAI MCP server expose?
StewAI exposes 59 tools: append_recipe_build_upload, approve_recipe_budget, begin_recipe_build_upload, bind_recipe_resource, cancel_recipe_activity, and 54 more. Their descriptions and schemas cost roughly 3,141 tokens of context every time the server is loaded.
Does the StewAI MCP server require authentication?
No. We connected to StewAI without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.
Is the StewAI MCP server still maintained?
StewAI 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 StewAI MCP server?
VerifyMCP ran 14 checks on StewAI, covering TLS certificate, Authorization, HTTPS, HSTS header and 10 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.