BRAINIAC Grant Compliance MCP server
software.brainiac/grant-compliancebrainiac.softwarestreamable-httpv1.0.1Scanned
Paid Grant Compliance API via x402. Unpaid tool calls return 402.
10 tools: 6 change things and 4 only read.
- Reads private data · 0
- Reads text others write · 10
- Can send data out · 0
- 4 findings
Tools listed without sign-in. Remote posture
With Anlyon
6 tools here change things. Govern them.
- Anlyon lists the tools and adopts none.
- Each tool you adopt gets approvals and receipts.
- Your agent never holds the key.
A tool your agent calls directly is not routed through Anlyon and is not governed by it. Anlyon Radar only lists and labels, and these labels are the same either way.
What the BRAINIAC Grant Compliance MCP server can do
The BRAINIAC Grant Compliance MCP server is published by brainiac.software, a domain the MCP Registry verified. It has 10 tools. It can create or change data (6 tools: grant-compliance_application-completeness, grant-compliance_expense-eligibility-check, grant-compliance_evidence-match, grant-compliance_deliverable-track and 2 more), but cannot delete data. 4 tools only read.
10 tools bring in text other people can write (grant-compliance_requirements-extract, grant-compliance_eligibility-check, grant-compliance_application-completeness and 7 more).
The fixed checks matched 4 findings (annotation-conflict). Each one comes with the text it matched.
Its remote endpoint lists its tools without sign-in, and its tools changed once since Anlyon Radar first saw them.
Last scanned Nov 20, 2026, version 1.0.1.
Tools
Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.
10 tools
Changes things 6Claude Code: ask
grant-compliance_application-completenessMark a requirement present only when an application section cites its id.Reads text others write1 finding
Why it is in this group
- The description's first verb is "mark": a word for a change.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Findings
- Warn
The server marks "grant-compliance_application-completeness" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":true}; The description's first verb is "mark": a word for a change.
Description, as the server wrote it Mark a requirement present only when an application section cites its id. The answer is not scored, and a complete set is not compliance. Price $0.04 USDC. POST /api/v1/grant-compliance/application-completeness. An unpaid call returns the x402 payment terms and does not run.
Annotations the server declares
- title: Check application completeness
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
grant-compliance_deliverable-trackRepeat the status supplied for each deliverable and compare an update date with a supplied due date.Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Repeat the status supplied for each deliverable and compare an update date with a supplied due date. accepted_by_caller is not an official acceptance. Price $0.03 USDC. POST /api/v1/grant-compliance/deliverable-track. An unpaid call returns the x402 payment terms and does not run.
Annotations the server declares
- title: Track supplied deliverables
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
grant-compliance_evidence-matchAttach evidence that cites a requirement id.Reads text others write1 finding
Why it is in this group
- The description's first verb is "attach": a word for a change.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Findings
- Warn
The server marks "grant-compliance_evidence-match" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":true}; The description's first verb is "attach": a word for a change.
Description, as the server wrote it Attach evidence that cites a requirement id. Evidence with no id is not matched, and the strength of the evidence is not judged. Price $0.05 USDC. POST /api/v1/grant-compliance/evidence-match. An unpaid call returns the x402 payment terms and does not run.
Annotations the server declares
- title: Match evidence to requirements
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
grant-compliance_expense-eligibility-checkApply only the supplied category decisions.Reads text others write1 finding
Why it is in this group
- The description's first verb is "apply": a word for a change.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Findings
- Warn
The server marks "grant-compliance_expense-eligibility-check" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":true}; The description's first verb is "apply": a word for a change.
Description, as the server wrote it Apply only the supplied category decisions. A category with no rule stays not supplied, and an eligible rule is not a funder decision. Price $0.04 USDC. POST /api/v1/grant-compliance/expense-eligibility-check. An unpaid call returns the x402 payment terms and does not run.
Annotations the server declares
- title: Check expenses against supplied rules
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
grant-compliance_reportCombine the supplied requirement, eligibility, budget, evidence, deliverable, and reporting checks.Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Combine the supplied requirement, eligibility, budget, evidence, deliverable, and reporting checks. The report does not approve the application or determine compliance. Price $0.12 USDC. POST /api/v1/grant-compliance/report. An unpaid call returns the x402 payment terms and does not run.
Annotations the server declares
- title: Prepare a grant compliance report
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
grant-compliance_report-validateMark a reporting obligation present only when the report cites its id.Reads text others write1 finding
Why it is in this group
- The name "grant-compliance_report-validate" says "validate": a word for reading.
- The description's first verb is "mark": a word for a change.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Findings
- Warn
The server marks "grant-compliance_report-validate" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":true}; The name "grant-compliance_report-validate" says "validate": a word for reading.
Description, as the server wrote it Mark a reporting obligation present only when the report cites its id. A present section is not accepted by a funder. Price $0.04 USDC. POST /api/v1/grant-compliance/report-validate. An unpaid call returns the x402 payment terms and does not run.
Annotations the server declares
- title: Validate a grant report
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
Only reads 4Show 4 read-only tools
grant-compliance_budget-validateSum the supplied lines, compare that sum with a supplied total, and check supplied category amount or percent caps.Reads text others writeNo findings
Why it is in this group
- The name "grant-compliance_budget-validate" says "validate": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Sum the supplied lines, compare that sum with a supplied total, and check supplied category amount or percent caps. No cap is assumed. Price $0.05 USDC. POST /api/v1/grant-compliance/budget-validate. An unpaid call returns the x402 payment terms and does not run.
Annotations the server declares
- title: Validate a grant budget
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
grant-compliance_deadline-extractRead Deadline lines that contain a YYYY-MM-DD date.Reads text others writeNo findings
Why it is in this group
- The description's first verb is "read": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Read Deadline lines that contain a YYYY-MM-DD date. Other dates in the guidelines are not turned into deadlines. Price $0.03 USDC. POST /api/v1/grant-compliance/deadline-extract. An unpaid call returns the x402 payment terms and does not run.
Annotations the server declares
- title: Extract grant deadlines
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
grant-compliance_eligibility-checkCompare each supplied rule with the supplied fact of the same name.Reads text others writeNo findings
Why it is in this group
- The description's first verb is "compare": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Compare each supplied rule with the supplied fact of the same name. A match is not an approval, and missing facts are not filled in. Price $0.04 USDC. POST /api/v1/grant-compliance/eligibility-check. An unpaid call returns the x402 payment terms and does not run.
Annotations the server declares
- title: Check supplied eligibility rules
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
grant-compliance_requirements-extractRead Requirement lines and structured requirements.Reads text others writeNo findings
Why it is in this group
- The description's first verb is "read": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Read Requirement lines and structured requirements. Other prose is not turned into a grant rule. Price $0.04 USDC. POST /api/v1/grant-compliance/requirements-extract. An unpaid call returns the x402 payment terms and does not run.
Annotations the server declares
- title: Extract grant requirements
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.
Exfil surface
Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.
No private-data, untrusted-input, outbound path in this server alone: no tool is tagged private-data or outbound.
- Reads private data0
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write10
- Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
- grant-compliance_application-completeness
- grant-compliance_budget-validate
- grant-compliance_deadline-extract
- grant-compliance_deliverable-track
- grant-compliance_eligibility-check
- grant-compliance_evidence-match
- grant-compliance_expense-eligibility-check
- grant-compliance_report
- grant-compliance_report-validate
- grant-compliance_requirements-extract
- Can send data out0
- Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.
Remote posture
What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.
Looked at Nov 20, 2026, 19:33 UTC, unchanged since Nov 20, 2026. No credentials were sent and no tool was called. What is looked at.
- Reachable
- yes
- HTTP status of an anonymous initialize
- 200
- tools/list served without credentials
- yes
- Tools that change things, listed without credentials
- 6
- Protocol version
- 2025-06-18
- WWW-Authenticate on 401
- not observed
- resource_metadata in WWW-Authenticate
- not observed
- RFC 9728 protected resource metadata
- not observed
- Authorization servers
- not observed
- Legacy HTTP+SSE transport
- no
- Dynamic client registration
- not observed
- Client ID metadata documents
- not observed
- WarnThe whole server
The endpoint served tools/list without credentials, and the list has 6 tools that change things (6 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://www.brainiac.software/mcp/grant-compliance: tools/list returned 10 tools to an anonymous client, including grant-compliance_application-completeness (write), grant-compliance_expense-eligibility-check (write), grant-compliance_evidence-match (write), grant-compliance_deliverable-track (write), grant-compliance_report-validate (write) and 1 more
Findings
Matches of fixed checks, with the text they matched.
The server marks "grant-compliance_application-completeness" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":true}; The description's first verb is "mark": a word for a change.
The server marks "grant-compliance_expense-eligibility-check" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":true}; The description's first verb is "apply": a word for a change.
The server marks "grant-compliance_evidence-match" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":true}; The description's first verb is "attach": a word for a change.
The server marks "grant-compliance_report-validate" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":true}; The name "grant-compliance_report-validate" says "validate": a word for reading.
History
Changes to its tool definitions and to its remote endpoint, newest first.
Tools10 changed.~10 changedView diff
- Changed:grant-compliance_application-completenessChanges thingsinputSchemaannotations
- Changed:grant-compliance_budget-validateOnly readsinputSchemaannotations
- Changed:grant-compliance_deadline-extractOnly readsinputSchemaannotations
- Changed:grant-compliance_deliverable-trackChanges thingsinputSchemaannotations
- Changed:grant-compliance_eligibility-checkOnly readsinputSchemaannotations
- Changed:grant-compliance_evidence-matchChanges thingsinputSchemaannotations
- Changed:grant-compliance_expense-eligibility-checkChanges thingsinputSchemaannotations
- Changed:grant-compliance_reportChanges thingsinputSchemaannotations
- Changed:grant-compliance_report-validateChanges thingsinputSchemaannotations
- Changed:grant-compliance_requirements-extractOnly readsinputSchemaannotations
Install
Pinned to version 1.0.1. Values in angle brackets are yours to fill in.
claude mcp add --transport http grant-compliance https://www.brainiac.software/mcp/grant-complianceclaude mcp add --transport http grant-compliance https://www.brainiac.software/mcp/grant-complianceRun in a terminal.
Claude Code permissions
Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.
{
"permissions": {
"allow": [
"mcp__grant-compliance__grant-compliance_requirements-extract",
"mcp__grant-compliance__grant-compliance_eligibility-check",
"mcp__grant-compliance__grant-compliance_budget-validate",
"mcp__grant-compliance__grant-compliance_deadline-extract"
],
"ask": [
"mcp__grant-compliance__grant-compliance_application-completeness",
"mcp__grant-compliance__grant-compliance_expense-eligibility-check",
"mcp__grant-compliance__grant-compliance_evidence-match",
"mcp__grant-compliance__grant-compliance_deliverable-track",
"mcp__grant-compliance__grant-compliance_report-validate",
"mcp__grant-compliance__grant-compliance_report"
],
"deny": []
}
}Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as grant-compliance. Review it before you use it.
Capability tags behind 10 rules
- mcp__grant-compliance__grant-compliance_requirements-extract untrusted-input
- mcp__grant-compliance__grant-compliance_eligibility-check untrusted-input
- mcp__grant-compliance__grant-compliance_application-completeness untrusted-input
- mcp__grant-compliance__grant-compliance_budget-validate untrusted-input
- mcp__grant-compliance__grant-compliance_expense-eligibility-check untrusted-input
- mcp__grant-compliance__grant-compliance_evidence-match untrusted-input
- mcp__grant-compliance__grant-compliance_deliverable-track untrusted-input
- mcp__grant-compliance__grant-compliance_report-validate untrusted-input
- mcp__grant-compliance__grant-compliance_deadline-extract untrusted-input
- mcp__grant-compliance__grant-compliance_report untrusted-input
Pin
Keep the decision: fail CI when the tools change, follow every change, or show a badge.
Pin in CI
Fail a build when the tools you reviewed are not the tools the server serves today.
curl -s "https://radar.anlyon.com/api/v1/servers/software.brainiac/grant-compliance/verify?hash=29bd0cb60c84a3d12cc586384f2ead76691a9ee922925071b916f63b8f2ae56b" | jq -e '.changed == false'Pinned hash 29bd0cb60c84, from Nov 20, 2026, 01:19 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/software.brainiac/grant-compliance/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/software.brainiac/grant-compliance)Source: MCP Registry. Synced Nov 20, 2026, 01:18 UTC.
BRAINIAC Grant Compliance MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the BRAINIAC Grant Compliance MCP server safe?
- No scan can promise that. What its definitions show: 10 tools, 6 of which can change, send or delete something, and 4 findings from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.
Can the BRAINIAC Grant Compliance MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the BRAINIAC Grant Compliance MCP server do things that cannot be undone?
- No tool is classed as irreversible: none of them sends, pays, publishes or merges, going by their definitions.
What tools does the BRAINIAC Grant Compliance MCP server have?
- 10 tools: 6 write, 4 read. grant-compliance_application-completeness, grant-compliance_expense-eligibility-check, grant-compliance_evidence-match, grant-compliance_deliverable-track, grant-compliance_report-validate, grant-compliance_report, grant-compliance_requirements-extract, grant-compliance_eligibility-check and 2 more.
Does the BRAINIAC Grant Compliance MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the BRAINIAC Grant Compliance MCP server send data to outside services?
- None of its tools sends, posts or publishes, or takes a recipient, channel or URL.
Has the BRAINIAC Grant Compliance MCP server changed its tools?
- Yes, once since Anlyon Radar started tracking it, most recently on Nov 20, 2026. Every change is on this page and in its Atom feed.