| Your AI coding agent can ask Rollbar how many users an error has reached, through get-metrics in our MCP server. Before… |
@rollbar |
Company |
Original |
2026-11-12 |
76 |
1 |
0 |
2 |
0 |
0 |
| You can now revoke a Rollbar invite sent to the wrong address.
Rollbar Lines, our software factory, wrote the requirem… |
@rollbar |
Company |
Original |
2026-11-11 |
62 |
2 |
0 |
0 |
0 |
0 |
| You can now send a teammate straight to the Improve card on your account dashboard with a link from its menu, the same … |
@rollbar |
Company |
Original |
2026-11-06 |
66 |
1 |
0 |
0 |
0 |
0 |
| Ask your coding agent to "walk me through what the user did before the error," and it can answer from the clicks, input… |
@rollbar |
Company |
Original |
2026-11-05 |
98 |
1 |
0 |
1 |
0 |
0 |
| Your coding agent can now write what it found onto the Rollbar item, like "Investigated the regression; the fix is in P… |
@rollbar |
Company |
Original |
2026-11-04 |
86 |
2 |
0 |
1 |
0 |
0 |
| Your AI agent can read the code that threw an error but not the request behind it. Our MCP server's get-item-details to… |
@rollbar |
Company |
Original |
2026-10-30 |
47 |
0 |
0 |
0 |
0 |
0 |
| When a resolved error comes back, your AI agent can't see in the code what your team tried last time. The list-item-eve… |
@rollbar |
Company |
Original |
2026-10-29 |
82 |
3 |
0 |
2 |
0 |
0 |
| Rollbar can now write the fix for a production error before anyone opens it. Agent Automation is on for every account. … |
@rollbar |
Company |
Original |
2026-10-27 |
86 |
0 |
0 |
1 |
0 |
0 |
| An AI agent can read every file in your repo and still not know which lines are throwing errors in production. The list… |
@rollbar |
Company |
Original |
2026-10-26 |
91 |
0 |
0 |
0 |
0 |
0 |
| In June 2021, one valid customer config change made 85% of Fastly's network return errors. Fastly caught the outage in … |
@rollbar |
Company |
Original |
2026-10-23 |
92 |
0 |
0 |
0 |
1 |
0 |
| Your AI agent can resolve the Rollbar item once it fixes the bug. update-item in our MCP server records the version wit… |
@rollbar |
Company |
Original |
2026-10-21 |
99 |
0 |
0 |
2 |
0 |
0 |
| Your AI agent spent an afternoon patching a bug Friday's deploy already fixed. The code gave no sign the errors stopped… |
@rollbar |
Company |
Original |
2026-10-19 |
90 |
0 |
0 |
0 |
0 |
0 |
| Your AI agent can read the retry loop in your code, but it can't see how often that loop gives up in production. Our MC… |
@rollbar |
Company |
Original |
2026-10-16 |
69 |
0 |
0 |
0 |
0 |
0 |
| LiteLLM's MCP endpoint accepted forged tokens, a flaw CISA lists as exploited (CVE-2026-59822). Upgrade to 1.84.0 or la… |
@rollbar |
Company |
Original |
2026-10-15 |
69 |
0 |
0 |
1 |
0 |
0 |
| A three-line fix to a production bug can still eat an afternoon of finding the file and rerunning tests. Hand the next … |
@rollbar |
Company |
Original |
2026-10-14 |
61 |
0 |
0 |
0 |
0 |
0 |
| We're rolling out personal access tokens, so each teammate gets their own Rollbar API token. Each one carries that pers… |
@rollbar |
Company |
Original |
2026-10-13 |
60 |
0 |
0 |
0 |
0 |
0 |
| A Rollbar item groups repeated occurrences of one error. The list-occurrences tool in our MCP server returns each occur… |
@rollbar |
Company |
Original |
2026-10-12 |
73 |
0 |
0 |
0 |
0 |
0 |
| ArcadeDB's MCP server let a user with read permission fetch the database's cluster token, and that token was enough to … |
@rollbar |
Company |
Original |
2026-10-08 |
103 |
0 |
0 |
1 |
0 |
0 |
| To diagnose a Rollbar item, your AI agent needs its latest occurrence. The get-item-details tool in our MCP server retu… |
@rollbar |
Company |
Original |
2026-10-07 |
86 |
0 |
0 |
0 |
0 |
0 |
| When an error starts right after a release, your AI agent needs to know what shipped. The get-deployments tool in our M… |
@rollbar |
Company |
Original |
2026-10-02 |
104 |
0 |
0 |
1 |
0 |
0 |
| mcp-atlassian checked its tool allowlist when listing tools but not when calling them, so a client limited to one tool … |
@rollbar |
Company |
Original |
2026-10-01 |
139 |
0 |
0 |
1 |
0 |
2 |
| A stack trace shows your AI agent one error but not how often it happens. The get-top-items tool in our MCP server retu… |
@rollbar |
Company |
Original |
2026-09-30 |
107 |
1 |
0 |
2 |
0 |
0 |
| Rollbar can now run root cause analysis on an error before anyone opens it. Write one rule with an environment and a se… |
@rollbar |
Company |
Original |
2026-09-29 |
78 |
0 |
0 |
0 |
0 |
0 |
| If your agent's permissions are enforced when it lists tools and not when it calls them, anything that knows a tool nam… |
@rollbar |
Company |
Original |
2026-09-24 |
105 |
0 |
0 |
0 |
0 |
0 |
| An Every Occurrence rule with no filter attached pages you for errors you already know about. The bill for that arrives… |
@rollbar |
Company |
Original |
2026-09-23 |
98 |
0 |
0 |
0 |
0 |
0 |
| Session replay is usually something a person sits and watches. get-replay in our MCP server hands the payload to your c… |
@rollbar |
Company |
Original |
2026-09-22 |
230 |
5 |
0 |
7 |
0 |
2 |
| Before markets opened on Aug 1, 2012, Knight Capital's systems sent 97 automated emails about a router error. None were… |
@rollbar |
Company |
Original |
2026-09-18 |
94 |
0 |
0 |
0 |
0 |
0 |
| Wiring an agent to real production errors is the easy half. Running the tests is where our Resolve beta still bites. Co… |
@rollbar |
Company |
Original |
2026-09-17 |
56 |
0 |
0 |
0 |
0 |
0 |
| An agent hands you a patch for a production error. Nothing has run it.
A fix is only worth trusting once your test sui… |
@rollbar |
Company |
Original |
2026-09-16 |
90 |
0 |
0 |
0 |
0 |
0 |
| Your agent gets the stack trace and guesses. Give it the 30 seconds before the throw instead: the click, the failed fet… |
@rollbar |
Company |
Original |
2026-09-15 |
103 |
0 |
0 |
0 |
0 |
0 |
| An AI coding agent has no sense of priority. It works on the error you paste in, whether that one fired twice last nigh… |
@rollbar |
Company |
Original |
2026-09-14 |
216 |
4 |
0 |
4 |
0 |
0 |
| An item summary tells your agent an error is frequent. Its occurrences tell it the error only hits one environment afte… |
@rollbar |
Company |
Original |
2026-09-11 |
89 |
0 |
0 |
0 |
0 |
0 |
| A team in Google's SRE Workbook never declared an incident, worked it in the bug tracker for 13 days, and bumped a quot… |
@rollbar |
Company |
Original |
2026-09-10 |
97 |
0 |
0 |
0 |
0 |
0 |
| An AI coding agent can read every branch in a function and still not know which one ran last night. Occurrence counts, … |
@rollbar |
Company |
Original |
2026-09-09 |
119 |
1 |
0 |
2 |
0 |
0 |
| An AI agent can write the fix, open the PR, and merge it. It still has no way to tell you whether the error stopped.
O… |
@rollbar |
Company |
Original |
2026-09-02 |
109 |
0 |
0 |
0 |
0 |
0 |
| Claude Code and Cursor can read every file in your repo. Neither can see which one threw in production last night.
Our… |
@rollbar |
Company |
Original |
2026-08-25 |
126 |
1 |
0 |
1 |
0 |
1 |
| Sort an unfamiliar service's error list by occurrence count and read the top ten. That is the map of which code paths a… |
@rollbar |
Company |
Original |
2026-08-20 |
111 |
0 |
0 |
0 |
0 |
0 |
| In Rails and Django, Rollbar tracks who hit each error automatically. Everywhere else you pass a person object with an … |
@rollbar |
Company |
Original |
2026-08-19 |
108 |
0 |
0 |
0 |
0 |
0 |
| Empty dashboard right after installing Rollbar usually means nothing is wrong, your app just hasn't thrown yet. The Bro… |
@rollbar |
Company |
Original |
2026-08-18 |
91 |
0 |
0 |
0 |
0 |
1 |
| New in beta: Resolve AI Agent. It turns a production error into a pull request, with your own test results attached so … |
@rollbar |
Company |
Original |
2026-08-12 |
77 |
3 |
2 |
0 |
0 |
0 |
| 2/ Same error, MCP server connected. Claude pulled the occurrence data and deploy diff, found the config change that br… |
@rollbar |
Company |
Original |
2026-08-12 |
89 |
2 |
0 |
0 |
0 |
0 |
| Giving your coding agent access to Rollbar used to mean one access token per project.
The Rollbar MCP server now takes… |
@rollbar |
Company |
Original |
2026-07-30 |
104 |
4 |
0 |
1 |
0 |
0 |