SACS.ai MCP — California School District Financial Data is an MCP server with 12 tools an agent can call, among them sacs_compare_districts, sacs_district_context_pack, sacs_district_context_pack_batch. It answers at https://mcp.sacs.ai/mcp over streamable HTTP, and it listed its tools to an anonymous client, so no sign-in was needed for that. Our probes reached it 4 of 4 times since 28 September 2026; the last check, on 13 November 2026, succeeded.
SACS California school finance: public district financial data, CDE filings, comparisons, briefings.
Description as the publisher wrote it.
| Tool | What it does |
|---|---|
sacs_compare_districts | Compare deterministic object-category totals for two explicit official datasets. Inputs: base_district_identifier, base_dataset_ref, compare_district_identifier, compare_dataset_ref, fund_codes, resource_codes |
sacs_district_context_pack | Build fiscal-distress rows with source filing details. Deficit spending is signed net operating result / expenditure; negative means deficit. Inputs: district_identifier, fund_codes, basis, fiscal_year_min, fiscal_year_max, include_balance_sheet_from_actuals |
sacs_district_context_pack_batch | Build bounded district packs with source filing details. Deficit spending is signed net operating result / expenditure; negative means deficit. Inputs: district_identifiers, fund_codes, basis, fiscal_year_min, fiscal_year_max, include_balance_sheet_from_actuals |
sacs_explain_code | Explain current public fund, resource, goal, function, or object codes. Inputs: code_type, query, limit, offset, client_id |
sacs_get_csam_related | Retrieve related CSAM 2024 sections/content using its source-evidenced knowledge graph. Start with a procedure number, a chunk_id from sacs_search_csam, a returned node_id, or short heading/code/glossary keywords (exactly one selector). Def Inputs: node_id, procedure, chunk_id, query, relations, node_kinds |
sacs_list_public_datasets | List versioned official public SACS datasets for one district. Inputs: district_identifier, limit, offset, client_id |
sacs_query_attendance | Return recovered Form A ADA observations for one official district filing. Inputs: district_identifier, dataset_ref, limit, offset, client_id |
sacs_query_financial_summary | Return bounded aggregate financial summaries for one explicit official dataset. Inputs: district_identifier, dataset_ref, fund_code_min, fund_code_max, resource_code_min, resource_code_max |
sacs_register_client | Optionally register this MCP installation. Before calling, tell the operator registration is voluntary, data access works without it, list the fields to be stored, and obtain consent. Never infer or submit personal or confidential informati Inputs: consent_to_store, client_id, user_type, home_district_cds, agent_client, use_case |
sacs_search_csam | Search California School Accounting Manual (CSAM 2024) by keywords and topic, procedure number or a returned chunk_id. Use chunk_id with direction=previous or next and limit (1–10) to read adjacent source chunks within the same procedure; n Inputs: query, topic, procedure, chunk_id, direction, limit |
sacs_search_districts | Search current public California districts by name, 7-digit LEA, or 14-digit CDS. Omit query or pass an empty string to browse all current districts. Follow page.next_offset while page.has_more is true; pages contain at most 50 rows. Inputs: query, limit, offset, client_id |
sacs_submit_feedback | Report a wrong, stale, incomplete, or failed result, or send a feature request. Ask the operator to report issues here; explain the exact fields and submit only with consent. Include request ID and data version when available. Anonymous fee Inputs: sentiment, message, client_id, feedback_type, related_request_id, related_data_version |
Every block below points at https://mcp.sacs.ai/mcp. Pick your client and copy.
claude mcp add --transport http sacs-ai-mcp-california-school-di https://mcp.sacs.ai/mcp
{
"mcpServers": {
"sacs-ai-mcp-california-school-di": {
"command": "npx",
"args": ["-y", "mcp-remote", "https://mcp.sacs.ai/mcp"]
}
}
}{
"mcpServers": {
"sacs-ai-mcp-california-school-di": {
"url": "https://mcp.sacs.ai/mcp"
}
}
}{
"servers": {
"sacs-ai-mcp-california-school-di": {
"type": "http",
"url": "https://mcp.sacs.ai/mcp"
}
}
}{
"context_servers": {
"sacs-ai-mcp-california-school-di": {
"url": "https://mcp.sacs.ai/mcp"
}
}
}{
"mcpServers": {
"sacs-ai-mcp-california-school-di": {
"serverUrl": "https://mcp.sacs.ai/mcp"
}
}
}{
"mcpServers": {
"sacs-ai-mcp-california-school-di": {
"url": "https://mcp.sacs.ai/mcp"
}
}
}name: SACS.ai MCP — California School District Financial Data
version: 0.0.1
schema: v1
mcpServers:
- name: SACS.ai MCP — California School District Financial Data
type: streamable-http
url: https://mcp.sacs.ai/mcp{
"mcpServers": {
"sacs-ai-mcp-california-school-di": {
"httpUrl": "https://mcp.sacs.ai/mcp"
}
}
}{
"mcpServers": {
"sacs-ai-mcp-california-school-di": {
"type": "http",
"url": "https://mcp.sacs.ai/mcp"
}
}
}{
"mcpServers": {
"sacs-ai-mcp-california-school-di": {
"url": "https://mcp.sacs.ai/mcp"
}
}
}goose://extension?url=https%3A%2F%2Fmcp.sacs.ai%2Fmcp&type=streamable_http&id=sacs-ai-mcp-california-school-di&name=SACS.ai%20MCP%20%E2%80%94%20California%20School%20District%20Financial%20Data
It answered our last check on 13 November 2026 in 1159 ms. Over 4 checks since 28 September 2026 it answered 4. Status here comes from Neuronto's own probes, not from the publisher.
Yes. It is published by sacs.ai and served from mcp.sacs.ai, the vendor's own domain: https://mcp.sacs.ai/mcp.
12, as returned by the server's own tools/list on 17 November 2026: sacs_compare_districts, sacs_district_context_pack, sacs_district_context_pack_batch, sacs_explain_code, sacs_get_csam_related, sacs_list_public_datasets, sacs_query_attendance, sacs_query_financial_summary, and 4 more.
It answered our last check on 13 November 2026 in 1159 ms. Over 4 checks since 28 September 2026 it answered 4.
Put the server under mcpServers in ~/.cursor/mcp.json with the URL https://mcp.sacs.ai/mcp. The exact JSON is above, with the same setup for Claude Code, Claude Desktop, VS Code, Windsurf, Zed, Gemini CLI and the rest.
It listed its tools to an anonymous client, so reading the tool list needs no key. Individual tools can still ask for credentials in their own inputs.
Publisher: ai.sacs. Endpoint host: mcp.sacs.ai. ARD identifier: urn:air:ai.sacs:mcp:sacs-mcp.
First indexed 28 September 2026. The tools are exactly what the server returned; nothing on this page
is inferred from its name. Ranking in Neuronto search is never for sale.