pulsemcp/admitbase · v2.0.0
Also listed as mcp-registry/com.admitbase/admissions · primary listing: mcp-registry/com.admitbase/admissions
As of 2026-10-23 19:07 UTC, AdmitBase is up with a Glimind reliability score of 97/100 (grade A). Over the last 30 days it answered 100% of Glimind's liveness checks. It had 7 outages in 90 days, with a median recovery of 3 minutes.
Admissions data and match scores for 500+ professional schools: law, medical, dental, MBA, pharmacy, vet, and optometry.
Claude Code
claude mcp add --transport http admitbase https://admitbase.com/api/mcp
Claude Desktop · Windsurf · Cline (mcpServers JSON)
{
"mcpServers": {
"admitbase": {
"type": "http",
"url": "https://admitbase.com/api/mcp"
}
}
}
Third-party server, listed as discovered. Review its source before installing.
3 of 3 tool(s) carry no readOnlyHint/destructiveHint annotations.
Annotate read-only tools with {"readOnlyHint": true}. Agents and gateways can then run them without a confirmation prompt, and route around destructive ones. How to fix →
No tool declares an outputSchema.
Declare outputSchema and return structuredContent (MCP 2025-06-18+). Agents can then parse results without guessing, and chain tools reliably. How to fix →
Paste-ready definitions with the problems above fixed. Changes marked verify need a human look. All of them as JSON: /v1/readiness/pulsemcp%2Fadmitbase/fixes
{
"name": "calculate_match_score",
"description": "Given a user's GPA and test score, calculate match category (Safety/Target/Reach/Far Reach), admission probability, and percentiles for one school or a ranked list. Public — no authentication required.",
"inputSchema": {
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"required": [
"program"
],
"properties": {
"gpa": {
"type": "number",
"maximum": 4,
"minimum": 0,
"description": "Cumulative GPA on a 4.0 scale (omit for ATAR-based Australian schools)"
},
"atar": {
"type": "number",
"maximum": 99.95,
"minimum": 0,
"description": "Australian Tertiary Admission Rank (0-99.95). Used instead of test_score/gpa for Australian schools, which select on a published ATAR cutoff."
},
"limit": {
"type": "integer",
"default": 10,
"maximum": 30,
"minimum": 1,
"description": "Number of top schools to return when no school_slug given"
},
"program": {
"enum": [
"law",
"medical",
"dental",
"veterinary",
"optometry",
"business",
"pharmacy"
],
"type": "string",
"description": "Program type"
},
"test_score": {
"type": "number",
"description": "Test score: LSAT 120-180, MCAT 472-528, DAT 1-30, OAT 200-400, GMAT/GRE for MBA. Omit for pharmacy (PCAT retired 2024 — GPA-only) and for ATAR-based Australian schools."
},
"school_slug": {
"type": "string",
"description": "If provided, calculate for this school only. Otherwise returns a ranked list."
},
"work_experience_years": {
"type": "number",
"description": "Years of full-time work experience (MBA programs only)"
}
},
"additionalProperties": false
},
"annotations": {
"readOnlyHint": true
},
"title": "Calculate match score"
}{
"name": "get_school_stats",
"description": "Get full admissions statistics for a specific school: GPA/test percentiles, acceptance rate, class size, tuition, employment outcomes. Public — no authentication required.",
"inputSchema": {
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"properties": {
"school_name": {
"type": "string",
"description": "School name to search for (partial match). Used when slug is unknown."
},
"school_slug": {
"type": "string",
"description": "School slug (e.g. \"harvard-law-school\"). Use search_schools to find slugs."
}
},
"additionalProperties": false
},
"annotations": {
"readOnlyHint": true
},
"title": "Get detailed school stats"
}{
"name": "search_schools",
"description": "Search professional schools (law, medical, dental, MBA, pharmacy, veterinary, optometry) by program type, name, or ranking range. Returns admissions stats and AdmitBase links. Public — no authentication required.",
"inputSchema": {
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"required": [
"program"
],
"properties": {
"limit": {
"type": "integer",
"default": 20,
"maximum": 50,
"minimum": 1,
"description": "Maximum number of results (default 20, max 50)"
},
"query": {
"type": "string",
"description": "School name search (partial match)"
},
"program": {
"enum": [
"law",
"medical",
"dental",
"veterinary",
"optometry",
"business",
"pharmacy"
],
"type": "string",
"description": "Type of professional school program"
},
"max_ranking": {
"type": "integer",
"description": "Only return schools ranked below this number"
},
"min_ranking": {
"type": "integer",
"description": "Only return schools ranked at or above this number"
}
},
"additionalProperties": false
},
"annotations": {
"readOnlyHint": true
},
"title": "Search professional schools"
}Get an email or webhook when this server's readiness drops by 10+ points, tool-poisoning text appears, or a tool breaks:
curl -X POST https://glimind.com/v1/subscriptions -H 'content-type: application/json' -d '{"tools":["pulsemcp/admitbase"],"email":"[email protected]"}'Agents: watch_tool({"toolId": "pulsemcp/admitbase"}) over MCP.
calculate_match_score ~411 tokenssearch_schools ~269 tokensget_school_stats ~163 tokensStatic checks of the advertised tools/list (schema, descriptions, annotations, tool-poisoning patterns, names, size) plus observed protocol, uptime, latency and contract changes. Read-only: no tool is ever called. Weights: schema 15, docs 20, safety 15, efficiency 15, compatibility 15, protocol 5, reliability 10, stability 5. Token counts are estimates (~3.6 characters per token).
Operator? Fix these, then re-check live. Embed the readiness badge:
[](https://glimind.com/server/pulsemcp%2Fadmitbase?ref=badge)
<a href="https://glimind.com/server/pulsemcp%2Fadmitbase?ref=badge"><img src="https://glimind.com/v1/readiness/badge/pulsemcp%2Fadmitbase.svg" alt="MCP agent-readiness"></a>
.. image:: https://glimind.com/v1/readiness/badge/pulsemcp%2Fadmitbase.svg :target: https://glimind.com/server/pulsemcp%2Fadmitbase?ref=badge :alt: MCP agent-readiness
Glimind records every version of this server's tool definitions in a signed, append-only transparency log. Current manifest sha256:b36594eb986d46ce…, first seen 2026-10-17, included at leaf 11161 of 53,964. Version history · verify what your client received.
Compare: most reliable ml servers · most reliable search servers
Glimind tells agents whether a server is up right now and how to call it, then fails over to a live alternative when it isn't.
Claude Code
claude mcp add --transport http glimind https://glimind.com/mcp
Claude Desktop · Windsurf · Cline (mcpServers JSON)
{
"mcpServers": {
"glimind": {
"type": "http",
"url": "https://glimind.com/mcp"
}
}
}
As of 2026-10-23 19:07 UTC, AdmitBase is up with a Glimind reliability score of 97/100 (grade A). Over the last 30 days it answered 100% of Glimind's liveness checks. It had 7 outages in 90 days, with a median recovery of 3 minutes.
AdmitBase advertises 3 tools, including calculate_match_score, get_school_stats, search_schools.
Point your MCP client at this streamable_http endpoint: https://admitbase.com/api/mcp
Glimind scanned all 3 tool definitions for tool-poisoning patterns — hidden or invisible characters, instructions that override the model, concealment from the user, requests to read credential or MCP config files, conversation exfiltration and cross-tool shadowing — and found none. This checks what the server tells the model, not what its code does; review the source before granting access to sensitive data.
Status page: 90-day uptime, every outage and how long it lasted.
Claim this listing to get the Verified operator marker, a remediation checklist and owner analytics, or embed the live badge from any of the tool pages above. Maintainers: alerts, deploy attestation and monthly reports.
Status is an automated estimate from Glimind's liveness checks (handshake and tool listing only; no tool is ever called) and may lag or differ from your network. Glimind is not affiliated with this server or its operator. Operator? Request a correction or opt out at https://glimind.com/opt-out.