Skip to main content
Glama
yousunjung84-edu

academyinfo-mcp

by yousunjung84-edu
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Hybrid

academyinfo-mcp

English | 한국어

academyinfo-mcp is an independent, read-only MCP server for factual queries and side-by-side comparison of Korean university disclosure indicators. It uses a bundled local snapshot: no API key and no runtime network connection are required.

This project is not affiliated with, endorsed by, approved by, sponsored by, or maintained by the Ministry of Education, KCUE, KEDI, data.go.kr, academyinfo.go.kr, or any university.

Quickstart

academyinfo-mcp runs with no install, no API key, and no login. It reads a bundled snapshot of Korean university disclosure indicators (대학알리미, KOGL Type 1) and answers factual queries and side-by-side comparisons from your AI assistant.

Claude Desktop

Add to claude_desktop_config.json (macOS: ~/Library/Application Support/Claude/), then restart Claude Desktop:

{
  "mcpServers": {
    "academyinfo": {
      "command": "npx",
      "args": ["-y", "academyinfo-mcp"]
    }
  }
}

Cursor

Add the same command/args shape to ~/.cursor/mcp.json (or a project .cursor/mcp.json), then reload the MCP server list.

Any MCP stdio client

npx -y academyinfo-mcp

The server speaks MCP over stdio (JSON-RPC on stdout, diagnostics on stderr).

Hosted endpoint (nothing installed)

For a client that cannot run a local process. A client that registers connectors by a URL field (for example claude.ai custom connectors) takes just the address:

https://academyinfo-mcp-433006350023.asia-northeast3.run.app/mcp

A client that takes a pasted mcpServers object takes this entry:

{
  "mcpServers": {
    "academyinfo": {
      "description": "대학알리미 공시데이터 — 488개 대학·캠퍼스 17개 지표 비교",
      "url": "https://academyinfo-mcp-433006350023.asia-northeast3.run.app/mcp"
    }
  }
}

No credentials, so no headers. Same bundled snapshot and same eight tools as the local form.

This is a personal deployment offered as-is: it can go away without notice, and it is not covered by any availability guarantee (see Support). For work you need to reproduce, prefer the local form and pin a version — academyinfo-mcp@0.4.0.

More on the pasted-object format, including the transport field that does not belong in it, is in examples/.

Try it

Ask your assistant something like:

"전남대와 부산대의 취업률과 경쟁률을 비교해줘."

The server never guesses an ambiguous name. "전남대학교" matches two campuses, so the first explore_universities call returns status: "ambiguous" with the candidates instead of a table:

전남대학교 → 2 candidates
    전남대학교 / 본교       (국립, 광주)
    전남대학교 / 제2캠퍼스  (국립, 전남)

Pick a campus and ask again (assistants usually do this follow-up on their own):

"전남대학교 본교와 부산대학교로 비교해줘."

The second call returns status: "ok" with each institution's values and the source, year, and unit attached — for example (2025 bundled snapshot):

대학

취업률

신입생 경쟁률

전남대학교 본교

57.6%

7.4:1

부산대학교

57.5%

9:1

This two-step flow is the designed behavior, not a failure: ambiguous names return candidate campuses instead of guessing, and comparisons never rank, score, or pick a winner — the numbers are presented as-is with provenance so you decide.

Related MCP server: paycoreDb

Evidence-scoped status

Implemented in this checkout:

  • a file-first, offline, read-only stdio server backed by the bundled 15118998 derivative database;

  • exactly eight registered MCP tools (the seven legacy tools plus explore_universities);

  • a schema-validated, KOGL-attributed data-only indicator catalog at data/seed/indicators.json;

  • Node engine >=22 <23 and the closed direct production dependency set @modelcontextprotocol/sdk@1.29.0, better-sqlite3@11.10.0, pino@10.3.1, and zod@4.4.3;

  • ambiguity handling that returns candidates rather than guessing, and factual comparisons without scores, ranks, winners, or recommendations;

  • a checkout-only stateless Streamable HTTP entry point (dist/src/http.js, POST-only, excluded from the npm package) alongside the packaged stdio entry point, with readOnlyHint/openWorldHint annotations on all eight tools.

Published: academyinfo-mcp@0.4.0 is live on the public npm registry (latest), published by hand from an isolated terminal ceremony (docs/manual-publish-runbook.md). The initial 0.1.0 release was smoke-verified with an anonymous npx -y academyinfo-mcp@0.1.0 install that resolves the exact registry tarball and lists all eight tools; later releases (0.1.1, 0.1.2, 0.2.0, 0.3.0, 0.3.1, 0.4.0) follow the same runbook.

Not yet performed (intentional, proportionate for a first solo release):

  • the formal no-compile npx proof across all three official Node 22 lanes (macOS/arm64, Windows/x64, Ubuntu glibc/x64) — only a single-machine smoke test was run. Separately, a one-off manual run (2026-07-24, outside CI) on Ubuntu 24.04 glibc/x64 with Node 22 installed academyinfo-mcp@0.1.1 anonymously, resolved better-sqlite3 from prebuilt binaries without compiling, and verified initialize, all eight tools, and an explore_universities call with JSON-RPC-only stdout; this is recorded observation, not the formal lane proof, and macOS/arm64 and Windows/x64 remain unverified;

  • the receipt-bound candidate→client→promotion evidence chain and an actual-client (Claude Desktop) receipt;

  • an approved unattended official download link or a completed annual refresh.

The package ships better-sqlite3@11.10.0 as its sole backend. It installs from prebuilt binaries on the maintainer's Node 22 macOS/arm64 lane and, in the one-off manual run above, on Ubuntu 24.04 glibc/x64; the full three-lane prebuilt-only matrix has not been independently proven. Exactly one backend ships.

Requirements

Use Node >=22 <23. Node 24 and later are not supported or claimed. The public support matrix is limited to Node 22 on:

  • macOS/arm64;

  • Windows/x64;

  • Ubuntu glibc/x64.

Those lanes are targets until public-install evidence is collected; local success is not public support evidence.

Local checkout use

The implemented local behavior can be exercised from a checkout:

npm install
npm run build
node dist/src/index.js

The last command starts an MCP stdio server. It does not provide an interactive shell. MCP protocol output is written to stdout; diagnostics must remain on stderr.

No API-key environment variable is required. ACADEMYINFO_DB_PATH may select another compatible local database; otherwise the bundled seed is used. Runtime tools do not write the database or contact an external service. This development checkout defines npm run doctor, npm run refresh:acquire-validate, and npm run refresh:verify-artifact. Only doctor has its compiled program included in the packed npm artifact, where it is a local package/data/runtime diagnostic; it does not prove public installation, backend selection, refresh acceptance, or release approval. The compiled refresh programs, their TypeScript build sources, and required development dependencies are excluded from the package, so both refresh commands are checkout-only protected-workflow internals, not supported installed-package commands. Direct local invocation is never an authoritative acquisition, writer, or release receipt.

Remote endpoint (Streamable HTTP, checkout-only)

The npm package remains stdio-only. A checkout (or a container image built from it) also provides a stateless Streamable HTTP entry point for remote MCP clients such as claude.ai custom connectors:

npm run build
PORT=8080 ALLOWED_HOSTS=<public-host> npm run start:http

  • POST /mcp accepts one JSON-RPC MCP request per call and answers a JSON response; GET (SSE streams) and DELETE (sessions) are not served because every request runs on a fresh server instance.

  • GET /healthz and GET /health answer 200 ok for deployment health checks (on Cloud Run run.app domains the Google frontend consumes the literal /healthz path, so external probes must use /health).

  • ALLOWED_HOSTS (comma-separated) enables DNS rebinding protection; leave it unset only behind a trusted proxy.

  • dist/src/http.js is excluded from the npm package, so installed npx academyinfo-mcp behavior is unchanged.

A remote deployment serves the same bundled point-in-time snapshot under the same attribution and disclaimer boundaries: it is not a live feed and does not guarantee the latest data, and the operator remains unaffiliated with the Ministry of Education, KCUE, KEDI, data.go.kr, academyinfo.go.kr, or any university.

Version pinning

The Quickstart uses the unversioned academyinfo-mcp, which resolves to the current latest (now 0.4.0). To pin a specific version instead, use academyinfo-mcp@0.4.0 in the args. Cursor and Codex use the same command/args shape as the Claude Desktop example; they are documented configurations and behave identically over MCP stdio.

Exact eight-tool scope

  1. list_sources

  2. list_indicators

  3. search_university

  4. get_university_metrics

  5. compare_universities

  6. explain_indicator

  7. validate_source_coverage

  8. explore_universities

The first seven contracts remain backward compatible. For client compatibility, tools/list registers explore_universities with this exact permissive Draft-07 outer input schema:

{
  "$schema": "http://json-schema.org/draft-07/schema#",
  "type": "object",
  "properties": {
    "university_queries": {},
    "indicators": {}
  },
  "additionalProperties": {}
}

The registered schema deliberately has no required keyword, and both property schemas plus additionalProperties are empty schemas. It is only the discovery boundary; the handler separately applies strict internal validation. The handler requires university_queries, rejects unknown top-level fields, accepts 1–10 unique trimmed query strings of 1–120 Unicode code points, and accepts an optional indicators array containing at most five unique supported nonempty indicator IDs. Invalid input fails before any journey is evaluated.

A valid explore_universities request is resolved against one local read-only snapshot. It is all-or-nothing. A missing or ambiguous university returns no partial metrics, comparisons, or explanations. Ambiguous matches return up to 20 repository-ordered candidates and never select one. The tool does not rank by metric values or substitute for a user's choice.

Every successful value or explanation retains source and license information, year or base year, unit, source column, derived/bundled status, and warnings. Missing source values remain explicit rather than being inferred.

Indicators and data boundary

The catalog contains exactly seventeen indicators from bundled dataset 15118998:

indicator

label

snapshot year

unit

competition_rate

신입생 경쟁률

2025

:1

fill_rate

신입생 충원율

2025

%

employment_rate

취업률

2025

%

scholarship_per_student

학생 1인당 연간 장학금

2025

원

avg_tuition

평균 등록금

2026

천원

admission_quota

입학정원

2025

명

graduates_count

졸업생수

2025

명

fulltime_faculty_count

전임교원수(학부+대학원)

2025

명

enrolled_students

재학생

2025

명

international_students

외국인 학생 수

2025

명

students_per_fulltime_faculty

전임교원 1인당 학생 수(학생정원기준)(학부+대학원)

2025

명

fulltime_faculty_ratio_quota

전임교원 확보율(학생정원기준)(학부+대학원)

2025

%

fulltime_faculty_ratio_enrolled

전임 교원 확보율(재학생 기준)(학부+대학원)

2025

%

fulltime_faculty_lecture_ratio

전임교원 강의 담당 비율

2025

%

education_expense_per_student

학생 1인당 교육비(학부+대학원)

2025

천원

dormitory_capacity_rate

기숙사 수용율(학부+대학원)

2025

%

books_per_student

학생 1인당 도서 자료 수(학부+대학원)

2025

권

These dates describe the currently bundled point-in-time snapshot, not a live feed or latest-data guarantee. The catalog is JSON data, validated by a closed static schema and packaged under the data license; it is not generated executable source. The database, manifest, and catalog are independently cross-checked.

An exact 0 in a rate, ratio, or per-student indicator is not served as a value. It arrives in missing_metrics as zero_not_aggregatable with the source text preserved, because such a cell cannot be distinguished from a placeholder and would otherwise enter an average unnoticed. Headcount zeros are served with a note, since an institution can genuinely have none. The evidence and the open question are in docs/zero-values.md.

Dataset 15139279 is not bundled, enabled, sampled, normalized, or used for default employment results. Live OpenAPI access, scraping, and granular employment behavior are outside this release.

Refresh safety summary

Refresh approval is semantic, not based on a frozen checksum or fixed column count. Acquisition is read-only and separate from the fixed-path repository writer. A refresh must preserve indexed raw cells and prove:

  • official source, workbook, and license identity;

  • one unique identity mapping and one unique mapping for each of the seventeen logical indicators;

  • fixed verified units and nondecreasing integer years;

  • exact row coverage: every source row maps once, with seventeen numeric-or-missing classifications;

  • missing values only for trimmed empty text or ASCII -;

  • exact nonnegative decimal parsing and round-trip safety, with no rounding.

A post-download SHA-256 is integrity, change, and audit evidence only. A changed checksum, institution set, values, allowed missingness, unrelated columns, or a valid 24/26-column workbook can pass when all semantic invariants pass. A prior-checksum match does not authenticate a source. See docs/refresh-release-runbook.md.

Automated acquisition currently stops at DOWNLOAD_LINK_MISSING: the reviewed canonical page is reachable and its license verifies, but it exposes no anonymously fetchable download link, and policy forbids guessing an endpoint or scraping a replacement. Refresh is therefore performed manually — see docs/manual-refresh.md.

Freshness and release behavior

A refresh incident has an immutable first-seen time and a seven-day (604800000 ms) deadline; metadata, ETag, or repeated-failure drift does not reset it. Invalid official timestamps do not become trusted times.

  • Equal reacquired bytes may close an incident only after origin/license/workbook validation and an administrator-attested verified-no-change receipt.

  • Differing bytes enter the changed lifecycle and close only when the matching release-data digest is promoted to latest.

  • Failed validation or release leaves the last-known-good data and public version in service.

  • Rolling back reopens the original changed-event clock; a corrected release uses a new SemVer.

Candidate publication is not completion. Public matrix evidence and actual Claude Desktop/macOS evidence must be joined into protected receipts before administrator-approved promotion. Rollback restores the prior latest, deprecates the bad version, preserves evidence, and reopens the incident when applicable. Candidate publication, promotion, and rollback all serialize npm registry mutation through the academyinfo-mcp-registry-mutation concurrency group with cancel-in-progress: false. After promotion, the uploaded post-mutation promotion.v1.json must be retained and persisted byte-identically in a protected immutable default-branch evidence commit at evidence/releases/<version>/promotion.v1.json before rollback is available. After rollback, its uploaded post-mutation rollback.v1.json must likewise be retained and persisted byte-identically at evidence/releases/<bad_version>/rollback.v1.json.

Public-install proof boundary

Local installs and local tarballs do not satisfy public acceptance. Each official lane must use a fresh home, cache, working directory, and configuration outside the checkout; an explicit public registry; no reachable local artifact; and exact:

npx -y academyinfo-mcp@<version>

The proof must record the installed application and the complete direct production dependency set—@modelcontextprotocol/sdk@1.29.0, better-sqlite3@11.10.0, pino@10.3.1, and zod@4.4.3 in the current single-backend package—plus each registry integrity; candidate tag and provenance/signature evidence; Node/OS/architecture (and glibc on Ubuntu); active Python/node-gyp/compiler traps with a demonstrated canary; verbose sanitized install logs; initialization; the exact eight-tool list and explore_universities schema; a bundled-data query; no-key behavior; and JSON-RPC-only stdout. A separately approved backend replacement requires the verifier and this closed dependency set to change together. Promotion is prohibited if any lane compiles native code, resolves another direct dependency version, reaches a local package, or lacks the required evidence.

Administrator prerequisites

Before candidate publication, an administrator must establish npm package identity/history and ownership, select an unused SemVer, confirm 2FA/trusted-publishing and provenance readiness, configure exactly the protected environments refresh-pr-writer, npm-candidate, public-candidate-proof, claude-desktop-client-proof, npm-promotion, and npm-rollback with required approvals and artifact retention, define protected ACADEMYINFO_RELEASE_ADMINISTRATOR as the exact receipt-authority identity, and define ACADEMYINFO_PUBLIC_INSTALL_VERIFIER_SHA256 plus ACADEMYINFO_RELEASE_RECEIPT_VERIFIER_SHA256 from the reviewed current verifier policy. The administrator must resolve the single-backend gate and approve the immutable candidate, client-proof, promotion, and any rollback receipts at their separate privilege boundaries. Every protected verifier call binds the configured authority and reviewed verifier bytes; neither receipt-provided identity nor caller-selected historical code is authority. No repository document selects a version or grants those approvals.

Support

This project is published as-is, without support. Issues, questions, and feature requests are not monitored and will generally not receive a reply, and there is no service level for availability, data freshness, or response time. It is a personal open-source project maintained on a best-effort basis by one person and is not operated by any institution.

You are welcome to use it under the licenses below, and to fork it if you need changes. Do not depend on it for anything where an unanswered question or an unpatched defect would matter.

License and privacy boundaries

  • Code is MIT licensed (LICENSE).

  • Bundled 15118998 data is a normalized derivative under KOGL Type 1 attribution requirements (DATA_LICENSE.md, NOTICE.md, and data/seed/LICENSE.15118998.md). Code and data licenses remain separate.

  • Release artifacts, receipts, logs, errors, examples, and MCP responses must not contain credentials, service keys, signed query strings, local user names, machine identifiers, or private filesystem paths.

  • Raw workbooks and signed download URLs are not package contents.

The normative scope and gates are maintained in the repository at PROJECT_CHARTER.md, NON_GOALS.md, and RELEASE_CHECKLIST.md.

Available Tools

8 tools
compare_universitiesCompare UniversitiesB
Read-only
Inspect

Compare verified local metrics for multiple universities when available.

ParametersJSON Schema
NameRequiredDescriptionDefault
indicatorsNo
university_namesNo

TDQS

B3/5.0
Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations include readOnlyHint=true and openWorldHint=false, and the description does not contradict them. It adds context by stating metrics are 'verified' and 'local' and may be unavailable ('when available'), which informs partial-result behavior. However, it does not explain what happens if metrics are missing or how results are structured, so it adds moderate value beyond the annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single sentence, front-loaded with the verb 'Compare', and every word contributes meaning. 'when available' is a useful qualifier, not filler, making it highly concise and well-structured.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Despite the tool's simplicity, the description leaves out critical invocation details. There is no output schema, so the description should explain what the comparison result looks like, but it doesn't. It also lacks parameter semantics and usage context, making it insufficient for an agent to invoke correctly in many situations.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters2/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema has two array parameters with no descriptions and 0% coverage. The description does not explain what 'indicators' or 'university_names' should contain, their format, or any constraints. The property names give a superficial hint, but the description fails to add meaningful parameter semantics.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the verb 'Compare' and the resource 'universities', with an implied scope of multiple universities. It differentiates from siblings like get_university_metrics (singular focus) and search_university (search), but the phrases 'verified local metrics' and 'when available' introduce some ambiguity about what exactly is being compared.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance is provided on when to use this tool versus alternatives like get_university_metrics or explore_universities. There are no exclusions or context that would help an agent decide between comparable tools, so the usage is only implied by the name.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

explain_indicatorExplain IndicatorA
Read-only
Inspect

Explain a v0.1 indicator with source metadata and verification status.

ParametersJSON Schema
NameRequiredDescriptionDefault
indicatorNo

TDQS

A3.6/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true, so the safe read nature is covered. The description adds value by specifying the explanation includes source metadata and verification status, giving the agent a clearer picture of the response content without contradicting annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, front-loaded sentence with no unnecessary words. It immediately states the verb, object, and key extra qualifiers, making it highly efficient and easy to parse.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple one-parameter read-only tool, the description covers the core purpose and hints at output content (source metadata, verification status). However, it omits any mention of return format, error behavior, or constraints, and does not connect to sibling tools. This is minimally adequate but leaves gaps.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters2/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema has a single 'indicator' parameter with zero description (0% schema coverage). The description only implies the parameter is the indicator to be explained, noting it is a v0.1 indicator, but does not compensate for missing schema details such as format, allowed values, or requiredness. This is minimal clarification.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description uses a specific verb 'explain' and a precise resource 'v0.1 indicator', and further clarifies it includes source metadata and verification status. This clearly distinguishes it from sibling tools like list_indicators, which merely list indicators, and compare_universities or search_university, which target different objects.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

No explicit guidance is given on when to use this tool versus alternatives. The description only states the action without indicating conditions, prerequisites, or exclusions. The sibling tools are not referenced, leaving the agent without direct decision support.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

explore_universitiesExplore UniversitiesB
Read-only
Inspect

Resolve universities and return factual side-by-side local indicator data.

ParametersJSON Schema
NameRequiredDescriptionDefault
indicatorsNo
university_queriesNo

TDQS

B3.3/5.0
Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true and openWorldHint=false, covering the core safety/behavioral profile. The description adds the 'factual' and 'local' qualifiers but does not disclose potential failure modes (e.g., unresolved queries, missing indicators) or output format specifics. No contradiction with annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single sentence with no filler. It is front-loaded with the main verb and resource, making it easy to scan. Every word contributes meaning.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple tool with two array parameters and no output schema, the description is minimally acceptable. It gives a high-level idea of inputs and output but lacks details on query syntax, expected indicator names, or side-by-side formatting. Sibling comparisons are not addressed, and there is no guidance on alternative tools.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must compensate. It implies the two parameters (university_queries and indicators) but does not elaborate on accepted formats, value sources (e.g., must come from list_indicators), or how 'resolve' handles ambiguous names. The parameter names are self-descriptive, but the description adds little beyond them.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a clear action ('Resolve universities') and a specific output ('factual side-by-side local indicator data'), which distinguishes it from listing sources and searching. However, it doesn't explicitly differentiate from the sibling 'compare_universities', so the purpose is clear but not fully unique.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance is provided about when to use this tool versus alternatives such as compare_universities, get_university_metrics, or search_university. There are no exclusions or contextual triggers, leaving the agent to infer appropriate usage.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

get_university_metricsGet University MetricsB
Read-only
Inspect

Return verified local metrics for one university when available.

ParametersJSON Schema
NameRequiredDescriptionDefault
indicatorsNo
university_nameNo

TDQS

B3.2/5.0
Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description adds context about data quality ('verified'), scope ('local'), and conditional availability ('when available'), which complements the readOnlyHint annotation. It does not describe return format or error behavior, but the annotation already covers the safety profile, so the added context earns a mid-range score.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, succinct sentence with no filler words. It is front-loaded with the core purpose and every word contributes to the meaning, making it highly concise and well-structured.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The description is minimal and omits critical information about the 'indicators' parameter and what 'metrics' entails. Given the absence of an output schema and 0% schema coverage, this leaves the agent without enough context for reliable invocation, especially since the tool has two parameters.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters2/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With 0% schema description coverage, the description should compensate for unclear parameters. It hints that university_name is the subject ('one university') but provides no explanation for the 'indicators' array or its role in filtering metrics. This is a significant gap in parameter understanding.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the action (return) and the resource (verified local metrics for one university), making the tool's purpose distinct from siblings like compare_universities or search_university. However, it doesn't explicitly name alternatives or differentiate itself from list_indicators, so it falls short of a perfect score.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage for retrieving metrics of a single university ('for one university'), but provides no explicit guidance on when to choose this tool over siblings such as search_university or compare_universities. No exclusions or alternative recommendations are given, making the usage context only implicit.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

list_indicatorsList IndicatorsB
Read-only
Inspect

List v0.1 file-first indicators enabled by default.

ParametersJSON Schema
NameRequiredDescriptionDefault

No parameters

TDQS

B3.2/5.0
Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The annotation readOnlyHint=true already indicates a safe read operation. The description adds that it lists only indicators 'enabled by default', which is a useful filtering trait. However, it does not disclose return format, pagination, or what 'file-first' means.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single sentence with no wasted words. The term 'v0.1' adds unnecessary verbosity and potential confusion, but overall it is concise and front-loaded with the main verb.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a tool with no output schema, the description should clarify what the response will contain. It does not explain what 'file-first indicators' are or what listing entails. The term 'file-first' is unexplained and likely confusing to an agent.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The tool has no parameters, so schema coverage is 100%. The baseline for zero parameters is 4. The description adds no parameter semantics, but none are needed.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states 'List ... indicators', which identifies the action and resource. It distinguishes from sibling 'list_sources' by focusing on indicators rather than sources. However, the terms 'v0.1' and 'file-first' are jargon that obscure the meaning.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides no guidance on when to use this tool versus alternatives like 'explain_indicator' or 'list_sources'. There is no mention of exclusions, prerequisites, or recommended use cases.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

list_sourcesList SourcesA
Read-only
Inspect

List bundled file-first academyinfo sources available in v0.1.

ParametersJSON Schema
NameRequiredDescriptionDefault

No parameters

TDQS

A4.4/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true and openWorldHint=false, providing the safety profile. The description adds useful context about the data being 'bundled file-first' and version-limited to v0.1, which goes beyond the annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

A single, front-loaded sentence that states exactly what the tool does and its scope. No filler or redundancy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple list tool with no parameters, no output schema, and strong annotations, the description is sufficient. It clearly identifies the resource type and version, covering the key context needed for safe invocation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The tool has zero parameters, so the description doesn't need to explain any. Baseline is 4 for no-param tools, and the description appropriately focuses on the result rather than inputs.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description uses a specific verb 'List' with a clear resource ('bundled file-first academyinfo sources') and scope ('available in v0.1'). It distinguishes from sibling tools like list_indicators by focusing on sources rather than indicators.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies when to use the tool (when you need to list available sources in v0.1) and provides version context. It doesn't explicitly mention alternatives or exclusions, but for a simple list tool the context is clear.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

search_universitySearch UniversityA
Read-only
Inspect

Search local file-first university records without guessing ambiguous matches.

ParametersJSON Schema
NameRequiredDescriptionDefault
queryNo

TDQS

A3.5/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true and openWorldHint=false, so the agent knows it is a safe read operation. The description adds valuable context: 'local file-first' indicates the data source and 'without guessing ambiguous matches' explains matching behavior. However, return format and error handling are not disclosed, which prevents a higher score.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single sentence, front-loaded with the verb 'Search', and every word adds meaning. It is concise and well-structured, with no wasted verbiage.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple tool with one parameter, the description gives some context but leaves gaps: no output schema, no explanation of return format, and the phrase 'without guessing ambiguous matches' is ambiguous itself. It does not clarify how this tool relates to sibling tools like explore_universities or validate_source_coverage, so the context is incomplete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters2/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema has one parameter ('query') with no description, and schema_description_coverage is 0%. The description does not mention the parameter at all, leaving the agent to guess what format or semantics 'query' expects. Since the description is the only source of parameter info, this is a significant gap.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states that the tool searches university records, with the qualifiers 'local file-first' and 'without guessing ambiguous matches' providing some scope. It distinguishes itself from siblings like explore_universities by implying exact-match behavior, but it does not explicitly name an alternative.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description gives some context ('file-first', 'without guessing ambiguous matches') that implies it is for exact local searches, but it does not explicitly say when to use it over alternatives or when not to. No exclusions are stated, and the sibling tools are not referenced.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

validate_source_coverageValidate Source CoverageB
Read-only
Inspect

Validate v0.1 source coverage, key policy, and bundled data boundaries.

ParametersJSON Schema
NameRequiredDescriptionDefault

No parameters

TDQS

B3.4/5.0
Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true and openWorldHint=false, so the description carries a lower burden. It adds context about what is being validated (v0.1 source coverage, key policy, and bundled data boundaries), but it doesn't disclose what the tool returns or how validation results are presented. This is acceptable but not rich beyond the annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single sentence, extremely concise, and front-loads the action ('Validate'). Every word earns its place; there is no repetition or filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the simplicity (0 params, no output schema), the description provides a basic understanding of what the tool validates. However, it doesn't explain what the user receives (e.g., a report, boolean, errors) or any prerequisites. This leaves some ambiguity about the tool's outcome, making it merely adequate.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The tool has zero parameters, so the schema fully covers parameter semantics (100% coverage). The description adds no parameter-specific details, but none are needed. Baseline for zero parameters is 4, and the description doesn't detract from that.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states a specific verb ('Validate') and resource ('source coverage, key policy, and bundled data boundaries'). It distinguishes this tool from siblings that list, search, or compare by focusing on a validation action. However, it doesn't explicitly contrast with any sibling, so it falls just short of a 5.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance is given on when to use this tool versus the related list/explore tools. The description implies usage for validation checks but doesn't state appropriate scenarios or exclusions. With multiple sibling tools, this lack of usage context makes it harder for an agent to select this tool confidently.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

  1. 8 tool updatesv0.3.1
    • First observedcompare_universities
    • First observedexplain_indicator
    • First observedexplore_universities
    • First observedget_university_metrics
    • First observedlist_indicators
    • First observedlist_sources
    • First observedsearch_university
    • First observedvalidate_source_coverage
Deploy Server
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

TDQS

A3.6/5.0

Scored across 8 tools

Disambiguation3/5

Most tools are distinct (list_sources, list_indicators, explain_indicator, validate_source_coverage), but explore_universities overlaps with search_university and compare_universities, as it also resolves universities and returns side-by-side data. This could confuse agents about which tool to use for multi-university comparisons.

Naming Consistency5/5

All tools follow a consistent verb_noun pattern in snake_case (list_, search_, get_, compare_, explain_, validate_, explore_). The verbs clearly indicate the action and the nouns describe the target, making the set predictable.

Tool Count5/5

With 8 tools, the server is well-scoped for a read-only academy information service. Each tool contributes a distinct function, and the count is within the ideal 3-15 range, avoiding both bloat and thinness.

Completeness4/5

The tool surface covers listing sources and indicators, searching/exploring universities, fetching metrics, comparing universities, explaining indicators, and validating coverage. Minor gaps such as a dedicated get_source tool or direct university detail retrieval are workarounds via existing tools, so overall coverage is strong for its stated purpose.

Maintenance

ActivityMaintained
ResponsivenessNo issues

Resources

Related MCP Connectors

Related MCP Servers

  • kr-elections-mcp

    taehyun-lim
    A
    license
    D
    quality
    B
    maintenance
    MCP server for South Korean election research, providing tools to search candidates, retrieve election results, and lookup campaign booklet texts using NEC open data and the krpoltext dataset.
    16
    1
    MIT

  • paycoreDb

    MaxenceBdu
    F
    license
    Not graded
    quality
    C
    maintenance
    Custom MCP server connected to a read-only SQLite database, exposing a schema resource and a query tool for safe data retrieval.
    -

  • eshare-mcp

    wineny
    F
    license
    Not graded
    quality
    B
    maintenance
    MCP server for searching and recommending Korean public resources (rooms, facilities, parking, etc.) using a static snapshot of the eShare OPEN API, with read-only tools for filtered search, detail, recommendation, and filter options.
    -

  • sbinfo

    reallygood83
    A
    license
    Not graded
    quality
    C
    maintenance
    MCP server for querying Korean school budget, unit projects, and special plans through the School Alert (학교알리미) open data API.
    MIT