PubSec Radar MCP server
io.github.Kabrawala/pubsec-sales-mcpKabrawalastreamable-httpv0.1.0Scanned
Federal sales intelligence: expiring-contract triggers, agency spend intel, deal qualification.
5 tools: 3 change things and 2 only read.
- Reads private data · 0
- Reads text others write · 0
- Can send data out · 0
- No findings
Tools listed without sign-in. Remote posture
With Anlyon
3 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 PubSec Radar MCP server can do
The PubSec Radar MCP server is published by the GitHub account Kabrawala. It has 5 tools. It can create or change data (3 tools: agency_spend_profile, generate_discovery_questions and qualify_opportunity), but cannot delete data. 2 tools only read.
None of its tools reads private data, brings in text other people write, or sends data out.
None of the fixed checks matched anything in its tool definitions. That is not a safety guarantee.
Its remote endpoint lists its tools without sign-in.
Last scanned Nov 16, 2026, version 0.1.0.
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.
5 tools
Changes things 3Claude Code: ask
agency_spend_profileUse this to answer "what does this agency actually buy, and from whom?" before a first call: total contract obligations, 3-year trend, top 10 vendors, and top 10 NAICS categories f…No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
Description, as the server wrote it Use this to answer "what does this agency actually buy, and from whom?" before a first call: total contract obligations, 3-year trend, top 10 vendors, and top 10 NAICS categories for the latest fiscal year with published data. Good queries name one agency, e.g. agency="HHS". Figures come from a daily snapshot of USAspending (latest published fiscal year plus a 3-year trend); the fiscal year and freshness are stated in the response. Federal only. Read the coverage caveats — in-progress fiscal years are partial, and intel-agency spend is never published.
generate_discovery_questionsUse this when prepping a meeting with a federal agency: it returns discovery questions tuned to public-sector selling (fiscal-year timing, contract vehicles, FedRAMP/ATO, incumbent…No findings
Why it is in this group
- The name "generate_discovery_questions" says "generate": a word for a change.
Description, as the server wrote it Use this when prepping a meeting with a federal agency: it returns discovery questions tuned to public-sector selling (fiscal-year timing, contract vehicles, FedRAMP/ATO, incumbents), grounded in the agency's live spending data where possible — each data-backed question cites the number that motivated it with a source URL. Good queries name the agency, what you sell, and the meeting type, e.g. agency="DHS", product_category="zero-trust network security", meeting_context="first_call". Add naics_code to surface expiring-contract questions.
qualify_opportunityUse this to pressure-test a federal deal: pass what you know per MEDDPICC dimension (leave unknowns empty) and get back an evidence-scored scorecard adapted for public sector — bud…No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
Description, as the server wrote it Use this to pressure-test a federal deal: pass what you know per MEDDPICC dimension (leave unknowns empty) and get back an evidence-scored scorecard adapted for public sector — budget authority instead of generic economic buyer, procurement vehicle as the paper process — with gap-closing questions and public-record evidence pulled automatically (name the incumbent_vendor and their real awards/end dates at the agency get attached). Scores measure evidence specificity, not truth; the response says what verified evidence looks like for each dimension.
Only reads 2Show 2 read-only tools
find_expiring_contractsUse this when prospecting or prepping a federal account and you want sales triggers: contracts at an agency that end soon, with the incumbent vendor, dollar values, and contracting…No findings
Why it is in this group
- The name "find_expiring_contracts" says "find": a word for reading.
Description, as the server wrote it Use this when prospecting or prepping a federal account and you want sales triggers: contracts at an agency that end soon, with the incumbent vendor, dollar values, and contracting office. Expiring contracts mean upcoming recompetes — the best time to displace an incumbent. Good queries name one agency and optionally a NAICS code, e.g. agency="DHS", naics_code="541512", window_days=90. Federal only (no state/local). Every response includes data-freshness and coverage caveats — read them; no data ≠ no spend.
incumbent_lookupUse this to answer "who am I displacing and when?": a vendor name (plus optional agency scope) returns their current and recent awards with values and end dates, flagging awards th…No findings
Why it is in this group
- The name "incumbent_lookup" says "lookup": a word for reading.
Description, as the server wrote it Use this to answer "who am I displacing and when?": a vendor name (plus optional agency scope) returns their current and recent awards with values and end dates, flagging awards that end within 12 months as displacement windows. Good queries use the vendor's registered name or a distinctive fragment, e.g. vendor="Booz Allen", agency="DHS". Federal only. Zero results ≠ no presence — check the caveats for name-matching tips.
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 untrusted-input or outbound.
- Reads private data0
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write0
- Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
- 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, 18:58 UTC, unchanged since Oct 22, 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
- 3
- 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 3 tools that change things (3 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://pubsec-sales-mcp.kabrawala.workers.dev/mcp: tools/list returned 5 tools to an anonymous client, including agency_spend_profile (write), generate_discovery_questions (write), qualify_opportunity (write)
Findings
Matches of fixed checks, with the text they matched.
No check matched anything in these tool definitions. That is not a safety guarantee.
History
Changes to its tool definitions and to its remote endpoint, newest first.
No change seen yet. Its tools are rescanned every day, and a remote endpoint is looked at once a week.
Install
Pinned to version 0.1.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http pubsec-sales https://pubsec-sales-mcp.kabrawala.workers.dev/mcpclaude mcp add --transport http pubsec-sales https://pubsec-sales-mcp.kabrawala.workers.dev/mcpRun 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__pubsec-sales__find_expiring_contracts",
"mcp__pubsec-sales__incumbent_lookup"
],
"ask": [
"mcp__pubsec-sales__agency_spend_profile",
"mcp__pubsec-sales__generate_discovery_questions",
"mcp__pubsec-sales__qualify_opportunity"
],
"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 pubsec-sales. Review it before you use it.
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/io.github.Kabrawala/pubsec-sales-mcp/verify?hash=731a8ad9f263cbe1733dbc711cbac9eac280ccdbdab4eaf6d4e38c6dcc661e1a" | jq -e '.changed == false'Pinned hash 731a8ad9f263, from Nov 16, 2026, 18:17 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/io.github.Kabrawala/pubsec-sales-mcp/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/io.github.Kabrawala/pubsec-sales-mcp)Source: MCP Registry. Synced Oct 21, 2026, 18:17 UTC.
PubSec Radar MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the PubSec Radar MCP server safe?
- No scan can promise that. What its definitions show: 5 tools, 3 of which can change, send or delete something, and 0 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 PubSec Radar MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the PubSec Radar 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 PubSec Radar MCP server have?
- 5 tools: 3 write, 2 read. agency_spend_profile, generate_discovery_questions, qualify_opportunity, find_expiring_contracts and incumbent_lookup.
Does the PubSec Radar MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the PubSec Radar MCP server send data to outside services?
- None of its tools sends, posts or publishes, or takes a recipient, channel or URL.
Has the PubSec Radar MCP server changed its tools?
- Not since Anlyon Radar started tracking it. Last scanned Nov 16, 2026.