MCP server for 104.com.tw job search platform
Free
Nothing to run from here
Stackwright Pro 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.
Open Installation—
p95 latency
—
call success
local
runs on your machine
—
calls last 7d
What it does
MCP tools for Stackwright Pro - Data Explorer, Security, ISR, and Dashboard generation
Quickstart
# 1 — run it from where its publisher ships it
npx -y @stackwright-pro/mcp
# 2 — ask your agent something
> MCP tools for Stackwright Pro - Data Explorer, Security, ISR, and Dashboard generation
Stackwright Pro is free: there is no plan to choose, no cap to set and nothing that can bill you.
Publishernot claimed
STAll 1 server
@stackwright-pro1 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 Stackwright Pro 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. It is scanned, signed and pinned to the version you choose — 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. Claude Code registers it in one command.
claude mcp add stackwright-pro-mcp -- npx -y @stackwright-pro/mcpReconnect, or start a new session, and the tools appear in the model’s tool list.
Free to install, and it runs from its publisher’s own package: no account, no key, no card.
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
62 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.
List all available API entities from OpenAPI specs or generated Zod schemas. Use this to discover what entities are available before generating endpoint filters. Returns entity names, endpoints, and field counts. Part of the Pro Otter Raft for building API-integrated Stackwright applications.
Takes no parameters.
Example callreturns →
Takes no parameters.
Example callreturns →
Validate an OpenAPI spec against the enterprise approved-specs configuration. Checks if the spec URL is on the allowlist and verifies SHA-256 hash integrity. Use this in enterprise environments where only pre-approved API specs are allowed. Fails build if spec is not approved or has been modified.
Takes no parameters.
Example callreturns →
Add an OpenAPI spec to the approved-specs allowlist in stackwright.yml. Computes the SHA-256 hash of the spec and adds it to the security configuration. Use this when onboarding a new API in enterprise environments.
Takes no parameters.
Example callreturns →
List all specs currently on the approved-specs allowlist. Shows spec names, URLs, and hash prefixes. Use this to audit what APIs are approved in the project.
Takes no parameters.
Example callreturns →
Configure Incremental Static Regeneration (ISR) for an API-backed collection. ISR allows API data to be cached and refreshed on a schedule, providing real-time data with the performance of static generation. Use this after stackwright_pro_generate_filter to set revalidation intervals.
Takes no parameters.
Example callreturns →
Configure ISR for multiple collections at once. More efficient than calling stackwright_pro_configure_isr multiple times. Provide different revalidation intervals based on data freshness requirements.
Takes no parameters.
Example callreturns →
Live data from API
Takes no parameters.
Example callreturns →
Generate a detail view page for a single API entity. Creates YAML content for displaying all fields of an individual record. Use this to create detail pages that complement collection listing pages.
Takes no parameters.
Example callreturns →
Takes no parameters.
Example callreturns →
Detect when a user
Takes no parameters.
Example callreturns →
Ensures pro packages are present in a project
Takes no parameters.
Example callreturns →
Takes no parameters.
Example callreturns →
Returns the next unanswered question for a phase as a plain JSON object \u2014 one question at a time. Returns { done: true } when all questions are answered or the phase has no questions. Call this in a loop: present the question in plain chat, get user reply, call record_answer, repeat.
Takes no parameters.
Example callreturns →
Records a single answer to a phase question. Appends to .stackwright/answers/{phase}.json incrementally. Idempotent \u2014 calling twice for the same questionId overwrites. Call after receiving each user reply in the conversational question loop.
Takes no parameters.
Example callreturns →
Save the user
Takes no parameters.
Example callreturns →
Parse and validate a specialist otter
Takes no parameters.
Example callreturns →
Write the question manifest to .stackwright/question-manifest.json. Call this after collecting and parsing questions from all otters via stackwright_pro_parse_otter_response.
Takes no parameters.
Example callreturns →
Save user answers for a phase to .stackwright/answers/{phase}.json. Pass rawAnswers directly from ask_user_question and the original manifest questions for label-to-value reverse mapping.
Takes no parameters.
Example callreturns →
Read saved answers for a phase from .stackwright/answers/{phase}.json. Returns { missing: true } when no answers exist yet \u2014 use this to skip phases safely in the execution loop.
Takes no parameters.
Example callreturns →
Get the agent name for a phase (e.g.
Takes no parameters.
Example callreturns →
Verify ECDSA P-384 signatures for all pipeline artifacts in .stackwright/artifacts/. Auto-discovers keys from .stackwright/pipeline-keys.json. Returns per-artifact verification status.
Takes no parameters.
Example callreturns →
Takes no parameters.
Example callreturns →
Returns a compact, LLM-friendly summary of a canonical schema derived programmatically from Zod. Includes required/optional fields, types, constraints, and
Takes no parameters.
Example callreturns →
Read pipeline state from .stackwright/pipeline-state.json. ${DESC}
Takes no parameters.
Example callreturns →
Atomic read\u2192modify\u2192write pipeline state. ${DESC}
Takes no parameters.
Example callreturns →
Check all phases have answer files in .stackwright/answers/. If phase is provided, check only that phase. ${DESC}
Takes no parameters.
Example callreturns →
Return phases whose dependencies are all satisfied (executed=true). Use to determine which phases can run next \u2014 enables wave-based execution. ${DESC}
Takes no parameters.
Example callreturns →
List phase artifacts in .stackwright/artifacts/ with completedCount/totalCount. ${DESC}
Takes no parameters.
Example callreturns →
Parse otter question-collection response \u2192 .stackwright/questions/{phase}.json. Specialists may also call this directly with a parsed questions array. ${DESC}
Takes no parameters.
Example callreturns →
Assemble execution prompt from answers + upstream artifacts. Foreman passes verbatim. ${DESC}
Takes no parameters.
Example callreturns →
Validate and write artifact to .stackwright/artifacts/. Returns retryPrompt on failure. ${DESC}
Takes no parameters.
Example callreturns →
Design language artifact
Takes no parameters.
Example callreturns →
Takes no parameters.
Example callreturns →
Generate authentication middleware and configuration for a Next.js Stackwright application. Writes
Takes no parameters.
Example callreturns →
Verify SHA-256 integrity of all Pro otter agent definitions. Call this at startup before discovering otters. Auto-discovers the otter directory from known paths. Returns verified/failed/unknown lists.
Takes no parameters.
Example callreturns →
List API-backed collections available for page generation. Reads from Data Otter artifact (.stackwright/artifacts/data-config.json) or stackwright.yml. Call this before generating pages that bind to data.
Takes no parameters.
Example callreturns →
Look up the data freshness strategy configuration from the user
Takes no parameters.
Example callreturns →
Workflow DSL \u2014 step definitions, auth blocks, field types, conditions
Takes no parameters.
Example callreturns →
Returns a structured summary of all canonical @stackwright-pro/types schemas, organized by domain. Use this to determine which otter owns a given schema and what artifact key to expect.
Takes no parameters.
Example callreturns →
Validates a YAML snippet against a canonical Zod schema before writing to disk. Returns actionable errors with
Takes no parameters.
Example callreturns →
Write or update a page
Takes no parameters.
Example callreturns →
Remove/rewrite stale scaffold files (blog posts, hardcoded not-found page) after the raft pipeline completes. ${DESC}
Takes no parameters.
Example callreturns →
Takes no parameters.
Example callreturns →
Compute the exact WCAG 2.1 contrast ratio between a foreground and background color. Returns the ratio and AA/AAA pass/fail flags. Use this to verify any foreground/background color pair before writing it to the token set. Accepts #RGB, #RRGGBB, hsl(...), or shadcn HSL format (
Takes no parameters.
Example callreturns →
Takes no parameters.
Example callreturns →
Compile stackwright.collections.yml \u2192 public/stackwright-content/_collections.json. Reads and validates the live-collections sidecar config file and emits the JSON sink consumed at runtime by PulseCollectionProvider.
Takes no parameters.
Example callreturns →
Compile stackwright.auth.yml \u2192 public/stackwright-content/_auth.json. Reads and validates the auth sidecar config file and emits the JSON sink consumed at app startup to configure auth middleware.
Takes no parameters.
Example callreturns →
Compile stackwright.integrations.yml \u2192 public/stackwright-content/_integrations.json. If no yml file exists, falls back to extracting integration metadata from _site.json (collections data is excluded \u2014 it lives in _collections.json).
Takes no parameters.
Example callreturns →
Run all Pro compile sinks (collections + auth + integrations) in sequence. Equivalent to running compile_collections, compile_auth, and compile_integrations individually. Use this for a full Pro prebuild pass.
Takes no parameters.
Example callreturns →
Compile stackwright.yml theme config \u2192 _theme.json. Delegates to compileTheme from @stackwright/build-scripts installed in the project.
Takes no parameters.
Example callreturns →
Compile stackwright.yml \u2192 _site.json. Delegates to compileSite from @stackwright/build-scripts installed in the project.
Takes no parameters.
Example callreturns →
Compile all pages content.yml files \u2192 page JSON files. Delegates to compilePages from @stackwright/build-scripts installed in the project.
Takes no parameters.
Example callreturns →
Compile a single page by slug. Delegates to compilePage from @stackwright/build-scripts installed in the project.
Takes no parameters.
Example callreturns →
Takes no parameters.
Example callreturns →
Takes no parameters.
Example callreturns →
Takes no parameters.
Example callreturns →
Takes no parameters.
Example callreturns →
Enumerate OpenAPI/AsyncAPI specs in the project
Takes no parameters.
Example callreturns →
Takes no parameters.
Example callreturns →
Takes no parameters.
Example callreturns →
MCP tools for Stackwright Pro - Data Explorer, Security, ISR, and Dashboard generation
Takes no parameters.
Example callreturns →
Freeyour plan
$0 forever
- Every tool, no call limit
- No card, no account needed
- Source published under a licence you can read
- Runs on your machine — nothing of it reaches our gateway
- Nothing to cap, because nothing bills
What counts against your monthly calls
| Tool | Unit | Calls used | Out of the allowance |
|---|
Nothing here is billable. Stackwright Pro costs nothing to install and nothing to call, 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: $8.42
$16.58 left
ATrust score 92 / 100
Release 0.2.0-alpha.130 · scanned 25 Aug 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 score92
Findings1 threat · 4 capability
Capabilityhigh
Coveragesource
Verificationnone
Surface digest5a9af28774a2666fef21befb4fd7a8d84cb7f26f190607135201fe2a9346ea84
Score vectorthreat 100 → client 92
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | high | capability blast radius (high) — client exposure if the model is manipulated | −6 |
| verification-discount | none | publisher verification (unlinked) — no provenance/repo link, but the shipped source was fully read | −2 |
| 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 (62 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 |
|---|---|---|
| stackwright_pro_verify_otter_integrity | no tags | |
| stackwright_pro_list_entities | no tags | |
| stackwright_pro_generate_filter | no tags | |
| stackwright_pro_validate_spec | no tags | |
| stackwright_pro_add_approved_spec | no tags | |
| stackwright_pro_list_approved_specs | no tags | |
| stackwright_pro_configure_isr | no tags | |
| stackwright_pro_configure_isr_batch | no tags | |
| stackwright_pro_generate_dashboard | no tags | |
| stackwright_pro_generate_detail_page | no tags | |
| stackwright_pro_clarify | no tags | |
| stackwright_pro_detect_conflict | no tags | |
| stackwright_pro_setup_packages | no tags | |
| stackwright_pro_present_phase_questions | no tags | |
| stackwright_pro_get_next_question | no tags | |
| stackwright_pro_record_answer | no tags | |
| stackwright_pro_save_build_context | no tags | |
| stackwright_pro_parse_otter_response | no tags | |
| stackwright_pro_save_manifest | no tags | |
| stackwright_pro_save_phase_answers | no tags | |
| stackwright_pro_read_phase_answers | no tags | |
| stackwright_pro_get_otter_name | no tags | |
| stackwright_pro_verify_artifact_signatures | no tags | |
| stackwright_pro_read_auth_manifests | no tags | |
| stackwright_pro_get_schema | no tags | |
| stackwright_pro_get_pipeline_state | no tags | |
| stackwright_pro_set_pipeline_state | no tags | |
| stackwright_pro_check_execution_ready | no tags | |
| stackwright_pro_get_ready_phases | no tags | |
| stackwright_pro_list_artifacts | no tags | |
| stackwright_pro_write_phase_questions | no tags | |
| stackwright_pro_build_specialist_prompt | no tags | |
| stackwright_pro_validate_artifact | no tags | |
| stackwright_pro_emit_event | no tags | |
| stackwright_pro_safe_write | no tags | |
| stackwright_pro_configure_auth | no tags | |
| stackwright_pro_list_collections | no tags | |
| stackwright_pro_resolve_data_strategy | no tags | |
| stackwright_pro_validate_workflow | no tags | |
| stackwright_pro_get_type_schemas | no tags | |
| stackwright_pro_validate_yaml_fragment | no tags | |
| stackwright_pro_write_page | no tags | |
| stackwright_pro_cleanup_scaffold | no tags | |
| stackwright_pro_write_workflow_container_page | no tags | |
| stackwright_pro_check_contrast | no tags | |
| stackwright_pro_derive_accessible_palette | no tags | |
| stackwright_pro_compile_collections | no tags | |
| stackwright_pro_compile_auth | no tags | |
| stackwright_pro_compile_integrations | no tags | |
| stackwright_pro_compile_all | no tags | |
| stackwright_pro_compile_theme | no tags | |
| stackwright_pro_compile_site | no tags | |
| stackwright_pro_compile_pages | no tags | |
| stackwright_pro_compile_page | no tags | |
| stackwright_pro_strip_legacy_integrations | no tags | |
| stackwright_pro_emit_env_local | no tags | |
| stackwright_pro_emit_providers_file | no tags | |
| stackwright_pro_emit_mock_ports | no tags | |
| stackwright_pro_list_specs | no tags | |
| stackwright_pro_describe_endpoint | no tags | |
| stackwright_pro_consolidate_integrations | no tags | |
| stackwright_pro_reconcile_page_auth_blocks | 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 digest5a9af28774a2666f
Scanned2026-08-25
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
Pinned to 0.2.0-alpha.130 — the install command below asks for that release. A pin is part of an install, so it is kept for this visit and written down when you install.
0.2.0-alpha.130
undated
installedNo release note was published with this version.
—
no reviews yet
Reviews are earned
Only accounts with at least 50 real tool calls against this server in the last 90 days can post. Ratings are weighted by how much the reviewer actually uses it, and publishers can reply once per review.
Reviews are earned
Writing one takes an account with at least 50 real tool calls against Stackwright Pro in the last 90 days. That is the whole gate — there is no other way to post, which is why the counts beside each review are worth reading.
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 an account with 50 real tool calls against it.