MCP.Market

Cypher MCP server

online · 100% uptime
by lonniev·io.github.lonniev/cypher-mcp·v0.9.0

Monetized graph answers via named Cypher queries — Tollbooth DPYC operator

A92/100grade A
What users say
No reviews yet
Be the first
Safety scan
A92/100

full report

Adoption
New

0 stars

Reviews

Write one

Nobody has reviewed Cypher yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

Cypher tools

Tool list not cached yet. `describe` through the gateway fetches it live.

Public scan report

scanner v0.1.10 · 2026-11-01 · same rubric, same numbers if you re-run it

no findings
  • –Code scanremote-only server, no package to scann/a
  • Live reliabilityremote reachable in 4157ms (auth required)17/20
  • –Tool poisoningtools not inspected (endpoint requires auth); not countedn/a
  • Auth qualityOAuth resource metadata advertised on 40115/15
  • Maintenancelast push 0 days ago15/15
  • Maintainer identityregistry namespace matches repository owner; GitHub account older than a year8/10
Overall 92/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

How Cypher compares

Against every graded MCP server, from our own scans and uptime checks. Updated after each scan run.

Safety score
92/100
higher than 95% of 48,255 servers
Uptime
100%
of our recent checks; the typical remote server answers 100%
Response time
425 ms
faster than 35% of 30,031 servers

Release history: 2 versions in the registry since 2026-08-24, latest 2026-10-21, typically one every 58 days.

Install Cypher in Claude Code, Cursor or VS Code

claude mcp add --transport http cypher-mcp https://cypher-mcp.fastmcp.app/mcp
Add to Cursor

What the publisher says

From the Cypher repository's README, as published. We do not edit it. Read it on GitHub

cypher-mcp

Monetized graph answers over Bitcoin Lightning. A Tollbooth-DPYC Operator that sells priced answers from a graph — operator-authored, parameterized, named Cypher query templates — not raw database access.

The OSS Neo4j MCP servers are a free pipe to a database the operator separately expenses (Neo4j invoice) and separately bills for (Stripe stack). cypher-mcp collapses infrastructure cost, application billing, and access control into one metered MCP surface: the operator stops selling seats and starts selling answers, settled in sats, with no Stripe stack and no Neo4j invoice passed to the customer.

Live at https://cypher-mcp.fastmcp.app/mcp.

How it works

Two planes, cleanly separated:

every other DPYC operator. It never knows a graph exists.

  • Settlement / identity plane — Neon + Nostr + Tollbooth, shared with

(graph.py), opened and torn down per request (no pool). The backing store is an implementation detail invisible to patrons, so it can be swapped without changing the MCP surface.

  • Value-delivery plane — Bolt → Neo4j, sealed inside the tool handlers

Three conceptual layers:

Status: live, with named tools. L1 + L2 are shipped and serving real,

billed answers — an operator adopted by an Authority, AuraDB-backed, with

refund-on-raise verified end to end. **Named tools are now live (L3 tool

synthesis): an operator can publishtool(key) to project a query as a

first-class, typed tool (e.g. cypherfindairlineflights(fromcity,

tocity)), priced individually in Pricing Studio. Per-key parametric pricing

formulas* remain a later step — see CHANGELOG.md.

Tools

Patron (priced):

supply only parameters; the operator owns the query text, and parameters bind as Cypher $params (never string-interpolated). You're charged only for a delivered answer — an unknown key, invalid parameters, or a failed query rolls back the debit (refund-on-raise).

  • cypherexecutequerybykey(key, params) — run a published query. You

Plus the standard DPYC surface from the wheel: cyphercheckbalance, cyphercheckprice, cypherpurchasecredits, Secure Courier, npub proof, Oracle delegation, account statements, constraint-based dynamic pricing, etc.

Operator-only (restricted, unpriced) — the authoring plane:

cypherlistqueries / cypherdeletequery

  • cyphercreatequery / cypherupdatequery / cyphergetquery /

a first-class, typed named tool (or retire it). See Named tools below.

  • cypherpublishtool(key) / cypherunpublishtool(key) — project a query as

Raw Cypher never reaches patrons — only named, parameterized templates.

Authoring in Neo4j's own UI — no second editor to learn

A DB-analyst refines templates in Neo4j Browser, not in a bespoke tool. cyphergetquery(key) returns the template plus an editurl — a deep link into the hosted Neo4j Browser (browser.neo4j.io) that pre-targets the operator's AuraDB and loads the statement in edit mode (cmd=edit). Refine it with autocomplete, run-to-test, visualization, and PROFILE; then save it back with cypherupdatequery. The template is just a string flowing over MCP — no files, no desktop, no exported bundles. The link carries the DBMS URI but never the password, and getquery is operator-only, so neither ever reaches a patron.

Named tools — publish a query as its own tool

Shortened. The full README is on GitHub.

Nothing above is checked by us. What we check is on the safety report.

Grade history

  • 2026-11-01restoreB → Ascore 92

Cypher: common questions

Is Cypher MCP server safe?
Yes, by our scan: it is graded A (92/100). Read the Cypher safety report
How do I install Cypher?
It runs remotely at cypher-mcp.fastmcp.app. Add it to Claude Code, Cursor, VS Code or Claude Desktop with the snippets above, or call it through the mcp.market gateway without installing anything.
Does Cypher need an API key?
No key to paste: it signs you in with OAuth when your client connects.
Is Cypher maintained?
The last commit was 3 days ago (2026-11-01). The latest release is v0.9.0.
Is Cypher up?
100% of our last 28 checks got an answer. We check remote servers about four times a day.
How does Cypher compare with other MCP servers?
safety score 92/100 (higher than 95% of 48,255 servers); uptime 100% (of our recent checks; the typical remote server answers 100%); response time 425 ms (faster than 35% of 30,031 servers). Full comparison.

More from lonniev →