# Neo4j Labs MCP Servers: SSRF and Data Modification via read_only Mode Bypass Through CALL Procedures

Advisory record · `GHSA-x3cv-r3g3-fpg9`

- **Identifiers:** `GHSA-x3cv-r3g3-fpg9` · `CVE-2026-35402` · `PYSEC-2026-2626`
- **State:** Confirmed
- **Severity:** CVSS 2.3 Low
- **Critical:** No
- **Weakness (CWE):** [CWE-284](https://cwe.mitre.org/data/definitions/284.html)
- **Tags:** [Broken access control](https://agentprime.io/advisories/tag/access-control.md)
- **Published:** 17 Apr 2026
- **Updated:** 13 Jul 2026
- **Reviewed by a person:** No

Published by the GitHub Advisory Database at 17 Apr 2026, 21:30 UTC. agentprime has not analysed this yet, so whether it affects any app is not known.

## Affected packages

- `mcp-neo4j-cypher` (PyPI): affected `<0.6.0`; fixed in `0.6.0`

## Machine-written summary

Summary written by Claude Haiku from the source advisory. Not reviewed by a person.

> The mcp-neo4j-cypher package, versions before 0.6.0, can have its read_only mode bypassed through certain APOC CALL procedures, allowing data modification and server-side request forgery. The source does not state what access an attacker needs beyond the ability to send queries to the server. Upgrade to version 0.6.0, which hardens the read_only checks; the source also recommends limiting the database credentials' permissions and restricting APOC procedures to those required.

Written 6 Nov 2026.

## Not analysed yet

We haven’t published our analysis of this Advisory yet. Once a person has reviewed it, this page will say what’s vulnerable, what has to be true for your app to be affected, and how to check.

## Severity and exploitation

- 2.3 Low, CVSS 4.0: `CVSS:4.0/AV:N/AC:L/AT:P/PR:L/UI:N/VC:L/VI:L/VA:N/SC:L/SI:L/SA:N`, from CNA (GitHub_M)

- **CISA KEV:** Not listed.
- **EPSS:** 0.0025, the 16th percentile, on 18 Nov 2026: FIRST’s estimate of the chance of exploitation in the next 30 days.

## Timeline

- 31 Oct 2026, 15:01 UTC: First seen by agentprime
- 31 Oct 2026, 15:01 UTC: [Confirmed by OSV](https://osv.dev/vulnerability/GHSA-x3cv-r3g3-fpg9)

## Sources

- [GitHub Advisory Database: GHSA-x3cv-r3g3-fpg9](https://github.com/advisories/GHSA-x3cv-r3g3-fpg9)
- [OSV: GHSA-x3cv-r3g3-fpg9](https://osv.dev/vulnerability/GHSA-x3cv-r3g3-fpg9)
- <https://github.com/neo4j-contrib/mcp-neo4j/security/advisories/GHSA-x3cv-r3g3-fpg9>
- <https://nvd.nist.gov/vuln/detail/CVE-2026-35402>
- <https://github.com/neo4j-contrib/mcp-neo4j>
- <https://github.com/neo4j-contrib/mcp-neo4j/releases/tag/mcp-neo4j-cypher-v0.6.0>

Facts on this page come from the GitHub Advisory Database (CC-BY 4.0), OSV and the other sources listed, as published. We don’t reproduce full advisory descriptions, which can contain exploit code.

## Check whether this affects you

A Match means an installed version is in the affected range above. Most don’t affect the app; agentprime hasn’t analysed this one yet.

- With the agentprime MCP server (<https://api.agentprime.io/mcp>), ask your agent to check the project: `check_lockfile` sends a lockfile, `check_packages` a list of installed packages, and both return the Matches and the upgrades that clear them. `get_advisory` returns this record. Setup: <https://agentprime.io/mcp.md>
- In a browser: <https://agentprime.io/check/> reads your lockfile in the browser, never uploading it.
- Whether it touches your code, with file and line: the Claude Code plugin, <https://agentprime.io/plugin.md>
- As JSON: <https://api.agentprime.io/v1/advisories/GHSA-x3cv-r3g3-fpg9>, or `POST https://api.agentprime.io/v1/match` with your packages (<https://agentprime.io/api.md>)

---

The web page: <https://agentprime.io/advisories/GHSA-x3cv-r3g3-fpg9/>. Everything for agents: <https://agentprime.io/llms.txt>.
