Lost updates
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
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.
Merged
PostHog’s fix for concurrent insight updates that lost a write in 7 of 11 pairs, co-authored by IsoKron
0 of 60
pairs lost an edit with our proposed Grafana fix on Grafana 13, against 30 of 30 unpatched
10 of 10
updates written through another editor’s document lock by Payload’s MCP plugin; its REST API refused all 10
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
- 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=yesis 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--- # commentseparator wrote only the first document and reported success, in 3 of 3 runs for each shape.kubectlapplied every document.
Write-safe MCP servers, at fixed prices
An audit or a rebuild, at a fixed price
Write-Safety Audit
$2,500
Fixed price
One server, up to 40 tools, one test account on one test tenant: the write paths first, plus a security review and what the tool catalog costs in context.
5 business days from the day access is in place
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.
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
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.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.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.
Latest research
Study,
Lost updates in four MCP servers: GitHub, Grafana, PostHog and Kubernetes
In all four MCP servers we audited, one write could undo another writer's change, each for a different reason.
Public audit,
GitHub MCP server v2.1.0: concurrent issue-field updates can silently lose changes
Two agents editing different fields of one issue lost a change in 19 of 30 pairs, while both calls reported success.
Public audit,
Grafana MCP server v2.2.0: dashboard patches skip the version check and can silently lose edits
Two simultaneous dashboard patches lost an edit in 30 of 30 pairs; the tool also skips the version check that rejects stale saves (10 of 10 through Grafana’s API).
Public audit,
PostHog MCP server: concurrent updates could silently lose a write in PostHog's own API
Concurrent updates to one insight lost a write in 7 of 11 pairs, and the bug was in PostHog’s API, which PostHog has fixed.
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.