Model Context Protocol server for Rollbar
Kestrel is installed from its publisher's own source and answers where it runs, so this marketplace is not in the path of a single call. There is no address here to send one to, and a panel that pretended otherwise would be showing you an answer we made up. Install it and call it from your own client — the Installation tab has the entry for each one.
What it does
Shows what your AI coding agents spend, and helps to spend less.
Quickstart
Install it the way its author documents:
The full guide: https://github.com/Widal-Inc/kestrel/releases/download/v0.2.0/kestrel-mcp.mcpb
Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.
Where are you running it?
Every route below installs the same thing and ends at the same approval screen. This one runs on your machine: your client starts Kestrel as a process under your own user, with your files and your network, so the tool surface below is what it can do to your computer rather than to a server somewhere else. Its scan result is on the Security tab — read the surface before you approve it.
Install it the way its author documents:
The full guide: https://github.com/Widal-Inc/kestrel/releases/download/v0.2.0/kestrel-mcp.mcpb
Tool surface
What the model actually sees. Descriptions are diffed on every release — see version history.
Read from its source code. A server that builds its tool list when it starts can list more tools than this.
Which agent logs Kestrel finds on this computer (Claude Code, Codex, Cowork), how many and how new, and what it cannot see. Use it first when unsure what there is, or when another answer is empty.
No parameter schema on file.
What the agents on this computer used, by tool, project and model, in dollars at list prices: spend when paid by the token, API value on a subscription, with each plan's price and limits where known. Use it for a question such as: what did my agents spend this week?
No parameter schema on file.
How the person pays, the plan's limits and how much of them is used, as far as Kestrel knows, and where each number comes from. Use it for questions about the plan, its limits or the percent used.
No parameter schema on file.
Proposals to spend less, each with the reason and the expected saving, from a replay of the logs. Use it when the person asks where to save or how to use less of the plan.
No parameter schema on file.
How often the context of Claude Code sessions was compacted (replaced by a summary), and how large it was before and after. Use it for questions about compaction or long sessions.
No parameter schema on file.
Spend by model, effort level and kind of work, such as reading, running commands or changing files. Use it for questions about which model or effort level costs the most.
No parameter schema on file.
Which agent sessions run on this computer now (Claude Code, Codex and Cowork), which of them wait for the person, and what to do next, with the ticket, context, cache and tokens of today of each session. Use it for questions such as: what are my agents doing right now?
No parameter schema on file.
Tokens, cost at list prices and sessions per ticket, from the git branch that each call names (a branch such as user/abc-322-login gives ABC-322). Use it for questions such as: what did each ticket cost this week?
No parameter schema on file.
The dollars and the plan's limits of each account that the agents used, such as a work and a personal Claude account, Cowork and Codex: tokens, spend or API value at list prices, and each plan's price. Use it for questions such as: which of my accounts used the most this week?
No parameter schema on file.
The open findings of Kestrel's security checks (the agents' settings, their actions, the code they changed, and cloud accounts checked on request), each with its kind, title, where it is, the controls of the frameworks that are on and the fix. Use it when the person asks about security risks or…
No parameter schema on file.
- Every tool, no call limit
- No card, and mcprush charges nothing for it
- Source published under MIT
- Runs on your machine — nothing of it reaches our gateway
- Nothing to cap, because mcprush bills nothing
What counts against your monthly calls
| Tool | Unit | Calls used | Out of the allowance |
|---|
Nothing here is billable: mcprush charges nothing to install Kestrel or to call it, at any volume.
Two independent axes, because powerful and malicious are different questions. The grade is threat only. The capability level is blast radius, and it is never a penalty on the grade — it is priced as one subtract-only term in the score, where you can see it.
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | high | capability blast radius (high) — client exposure if the model is manipulated | −6 |
| verification-discount | repo | publisher verification (public source) — no provenance, but the source is public and inspectable | −1 |
| coverage-honesty | source | inspection depth (source) — how much of the target the scan could see | −0 |
What the scan could actually read
A grade is only as meaningful as its coverage, so the scanner publishes its own depth before it publishes its result.
No tools were enumerated, so prompt-injection, capability and toxic-flow analysis had no tool surface to inspect. To grade a package’s real runtime tools, scan the running server: --command "npx -y <package>".
Capability — what it could do if the model were manipulated
Tags derived from each tool’s schema and the implementation, not from what the tool calls itself. high is the level these add up to.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| No per-tool rows for this release — see the note below. | ||
Toxic-flow graph
The lethal trifecta, checked as a graph rather than as a checklist: untrusted input, a sensitive source and an external sink have to meet before there is a path worth worrying about.
The public result for this release does not print the flow graph, so there is nothing to show here. That is not the same as "no paths were found": what the scan did read is above, under coverage.
Supply chain and provenance
This is the first scan of this surface here, so there is nothing yet to compare it against.
Every result on this tab comes from one deterministic pass over the published package — offline, rule by rule, and auditable line by line above. Same methodology version, same bytes, same score.
Release history
It installs from its repository rather than from a versioned package, so the command cannot be pinned to a release. The history below is for reading; the current release on file is 0.2.0.
No release note was published with this version.
One review per account, from a signed-in account that does not publish this listing. Nothing else is asked — you can say what you think before you install it. Publishers can reply once per review, and a review can be edited or deleted by whoever wrote it.
Any signed-in account that does not publish Kestrel can review it, once — before installing it or after. A review from an account that has installed it is marked as one.
Nobody has reviewed this listing. The rating on the card is the mean of the reviews written here and nothing else, so there is no rating until somebody writes the first — which takes a signed-in account that does not publish it, and nothing else.