CostBench MCP server
com.costbench/mcpcostbench.comstreamable-httpv1.1.0Scanned
Verified pricing, hidden costs, negotiation data, price changes & TCO for 3,390+ software products.
9 tools: 2 change things and 7 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
2 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 CostBench MCP server can do
The CostBench MCP server is published by costbench.com, a domain the MCP Registry verified. It has 9 tools. It can create or change data (2 tools: calculate_tco and estimate_llm_cost), but cannot delete data. 7 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 10, 2026, version 1.1.0.
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.
9 tools
Changes things 2Claude Code: ask
calculate_tcoTotal cost of ownership for a product and team size: sourced line items (licenses with price escalation, benchmark implementation), year-one + multi-year totals, effective per-seat…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.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it Total cost of ownership for a product and team size: sourced line items (licenses with price escalation, benchmark implementation), year-one + multi-year totals, effective per-seat cost. The defensible "true cost for an N-person team" answer.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: false
estimate_llm_costEstimate the cost of an LLM/API workload (input + output tokens) for a usage-priced provider (OpenAI, Anthropic, AWS Bedrock…) from its real rate card.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.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it Estimate the cost of an LLM/API workload (input + output tokens) for a usage-priced provider (OpenAI, Anthropic, AWS Bedrock…) from its real rate card.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: false
Only reads 7Show 7 read-only tools
compare_softwareSide-by-side pricing comparison of 2–4 products (starting price, enterprise tier, median annual cost, free tier, ratings).No findings
Why it is in this group
- The name "compare_software" says "compare": a word for reading.
Description, as the server wrote it Side-by-side pricing comparison of 2–4 products (starting price, enterprise tier, median annual cost, free tier, ratings).
Annotations the server declares
- readOnlyHint: true
- openWorldHint: false
discover_softwareFind software products by name search or criteria (category, max price, free tier).No findings
Why it is in this group
- The description's first verb is "find": a word for reading.
Description, as the server wrote it Find software products by name search or criteria (category, max price, free tier). Returns matching slugs to look up — use "query" to find the slug for a product name.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: false
get_negotiation_tipsSourced negotiation tactics for a product with success-likelihood (how to get a discount).No findings
Why it is in this group
- The name "get_negotiation_tips" says "get": a word for reading.
Description, as the server wrote it Sourced negotiation tactics for a product with success-likelihood (how to get a discount).
Annotations the server declares
- readOnlyHint: true
- openWorldHint: false
get_price_changesRecent software pricing changes CostBench detected against vendor pricing pages (increases, decreases, plan restructures) — dated, with before/after price bands and a source link.No findings
Why it is in this group
- The name "get_price_changes" says "get": a word for reading.
Description, as the server wrote it Recent software pricing changes CostBench detected against vendor pricing pages (increases, decreases, plan restructures) — dated, with before/after price bands and a source link. Filter by product slug, category, or lookback window. The "what changed lately" answer; each item links to the sourced record.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: false
get_price_historyDated per-quarter snapshots of a product's pricing page.No findings
Why it is in this group
- The name "get_price_history" says "get": a word for reading.
Description, as the server wrote it Dated per-quarter snapshots of a product's pricing page. Returns observations, NOT a trend figure — CostBench does not publish one, because diffing snapshots across renamed/restructured plan lineups is ~90% measurement artifact.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: false
get_pricingFull sourced pricing record for a software product: tiers, hidden costs, contract terms, market data, sentiment, negotiation tips, TCO scenarios, price history — every claim with i…No findings
Why it is in this group
- The name "get_pricing" says "get": a word for reading.
Description, as the server wrote it Full sourced pricing record for a software product: tiers, hidden costs, contract terms, market data, sentiment, negotiation tips, TCO scenarios, price history — every claim with its sources + a confidence/verification envelope.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: false
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, 18:36 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
- 2
- Protocol version
- 2025-03-26
- 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 2 tools that change things (2 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://costbench.com/mcp: tools/list returned 9 tools to an anonymous client, including calculate_tco (write), estimate_llm_cost (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 1.1.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http costbench https://costbench.com/mcpclaude mcp add --transport http costbench https://costbench.com/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__costbench__get_pricing",
"mcp__costbench__get_hidden_costs",
"mcp__costbench__get_negotiation_tips",
"mcp__costbench__get_price_history",
"mcp__costbench__compare_software",
"mcp__costbench__discover_software",
"mcp__costbench__get_price_changes"
],
"ask": [
"mcp__costbench__calculate_tco",
"mcp__costbench__estimate_llm_cost"
],
"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 costbench. 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/com.costbench/mcp/verify?hash=7b3bb544418e2c36e10246945d984d9e57e841a6bf521aabbe187835a2d4ea57" | jq -e '.changed == false'Pinned hash 7b3bb544418e, from Nov 10, 2026, 13:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/com.costbench/mcp/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/com.costbench/mcp)Source: MCP Registry · repository. Synced Oct 21, 2026, 17:53 UTC.
CostBench MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the CostBench MCP server safe?
- No scan can promise that. What its definitions show: 9 tools, 2 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 CostBench MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the CostBench 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 CostBench MCP server have?
- 9 tools: 2 write, 7 read. calculate_tco, estimate_llm_cost, get_pricing, get_hidden_costs, get_negotiation_tips, get_price_history, compare_software, discover_software and 1 more.
Does the CostBench MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the CostBench MCP server send data to outside services?
- None of its tools sends, posts or publishes, or takes a recipient, channel or URL.
Has the CostBench MCP server changed its tools?
- Not since Anlyon Radar started tracking it. Last scanned Nov 10, 2026.