Skip to content
IsoKron

New: MCP Write-Safety Requirements 0.9 and two studies

When AI agents write through your MCP server, changes can silently disappear. We find and fix that.

We audit MCP servers for security and write correctness, then rebuild their write paths or build new ones in your repository.

19 of 30pairs lost a change through the MCP server

0 of 28lost through GitHub’s own per-field API

Figure 1. GitHub MCP server v2.1.0, issue #3751: two agents edit different fields of one issue at once, and both calls report success. Three runs.

You ship an MCP server

We find the writes that silently go wrong before your customers’ agents do.

You’re adopting one

Before agents write through someone else’s server, find out what it gets wrong.

What our public research found, as of

7 of 100

popular MCP servers with write tools, sampled from the most-downloaded packaged servers in the official registry, can return a machine-readable “unknown” when a write’s outcome isn’t known. Read, not run.

100-server study

Merged

PostHog’s fix for concurrent insight updates that lost a write in 7 of 11 pairs, co-authored by IsoKron

Pull request #131620

0 of 60

pairs lost an edit with our proposed Grafana fix on Grafana 13, against 30 of 30 unpatched

Pull request #1518 (open)

10 of 10

updates written through another editor’s document lock by Payload’s MCP plugin; its REST API refused all 10

Payload audit

Research on public MCP servers, not client engagements. Every issue and pull request we filed, with its status

Public research on the GitHub, PostHog, Grafana, Kubernetes and Payload MCP servers

We test whether your MCP server’s writes actually land. We test the same way in public: independent audits of GitHub, Grafana, PostHog, Kubernetes and Payload, with findings, reproductions and upstream status published.

Why it matters

Three things we found in public MCP servers, and what each means for a team whose agents write through one.
  • Lost updates

    Two agents edit one record. Both are told “success”. One change is gone.

    In GitHub’s, Grafana’s and PostHog’s MCP servers, one of two simultaneous writes to one object could be lost while both calls reported success.
  • Safety switches

    A read-only switch that silently stays off.

    In GitHub’s MCP server, GITHUB_READ_ONLY=yes is read as false, so the server starts with write tools on and no warning.
  • Partial writes

    An apply that writes one document and reports success.

    In the Kubernetes MCP server, a multi-document apply with a ---  or --- # comment separator wrote only the first document and reported success, in 3 of 3 runs for each shape. kubectl applied every document.

Write-safe MCP servers, at fixed prices

An audit or a rebuild, at a fixed price

An audit with fix pull requests, or a rebuild of the write paths. The listed price is the price.

Write-path rebuild

$6,000

Fixed price in total, no blueprint needed

One existing or generated MCP server, up to 40 tools. We keep your server and rebuild its write paths and tool design in its own repository.

About two weeks; the date is agreed in writing before we start

Ongoing

Per-release regression check

$750

per month per server

Re-runs the write-path reproductions from the audit, or the tests from the rebuild or build, against up to four releases a month and reports what changed. More releases are quoted. Three-month minimum. Available after an audit, or as maintenance after a rebuild or build.

See it on the pricing page

The Write-Safety Audit leads with the write paths and also covers a security review, the tool catalog and its token cost, and fixes, a retest and an Evidence Pack. The security review is not a penetration test of the platform behind the server or of its OAuth provider. Servers behind OAuth sign-in are in the fixed price; testing two accounts or tenants against each other is not available yet. A second server in the same engagement is +$1,750, the per-task agent benchmark is quoted on request, and testing never touches production data. What the audit covers

New MCP servers (from $7,500, with the MCP blueprint as part of the price), add-ons such as a second server, and larger work are on the pricing page, with scope, turnaround, deliverables and exclusions for each.

How every finding in a client report is verified

  1. Step 1: Checked against a control

    Where the vendor has its own API, the same operation runs through it, so we know whether the bug is in the MCP server or in the platform behind it. For the lost-update finding, GitHub’s API lost 0 of 28.
  2. Step 2: Challenged by a separate AI refuter

    A separate AI, in a clean context, tries to explain the finding away. If it can, we drop it.
  3. Step 3: Reproduced and reviewed by a person

    A person reruns the reproduction and reads the evidence before it reaches the report.

Evidence: A finding we dropped

search_code found nothing on a private repo, and neither did GitHub’s own API, so we never reported it.

Our public audits say which of these checks their findings went through, and where a check fell short. More on the method

What you receive

Sample report

One entry per finding

Impact, reproduction, control, refuter result, confidence and a suggested fix.

Evidence Pack

Check the results yourself

An IsoKron Evidence Pack is the signed, timestamped record of an audit. You can check it on your own machine with one command, without trusting IsoKron’s servers.

Request an audit or a build

Tell us which server and what you need. We reply to confirm the scope, the price and the dates.