backscroll
MCPB · BACKSCROLL-0.13.1.MCPB
Search, retrieve, and diff the full output of past terminal commands recorded locally by backscroll.
Available components
Last scanned (3 hours ago)
Scores higher than 94% of MCPB servers
Category Developer Tools
How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score → Why this is hard to score →
Supply Chain Security0
- No malware scan is available for this kind of package: the supply-chain vendors we use do not cover it. This is a permanent gap in our coverage, not a finding about the package.Unverified
- Known CVEs could not be checked: we found no dependency list to check in this bundle: either it runs a compiled binary, whose bundled manifests we do not read, or none of the package.json, requirements.txt, pyproject.toml or uv.lock files it ships for its runtime declares a dependency we can read (a requirements.txt that only points at a setup.py project, a local path, or a nested requirements file we cannot follow counts as none).Unverified
- Install-script risk not yet assessed.Unverified
- Dependency health could not be checked: we found no dependency list to check in this bundle: either it runs a compiled binary, whose bundled manifests we do not read, or none of the package.json, requirements.txt, pyproject.toml or uv.lock files it ships for its runtime declares a dependency we can read (a requirements.txt that only points at a setup.py project, a local path, or a nested requirements file we cannot follow counts as none).Unverified
Provenance & Transparency100
- Source repository is publicly reachable at the declared URL. View diagnostics → Pass
- Cryptographically verified build provenance (signed, bound to soren-achebe/backscroll). View diagnostics → Pass
- Clear OSI-approved license (MIT).Pass
- Actively maintained (last published 61 days ago).Pass
- Publishes a security disclosure policy (SECURITY.md).Pass
Schema Quality & AI Usability69
- AI-judged instruction clarity (excellent).Pass
- Context-footprint check failed: tool/resource definitions use about 1105 tokens (~276/item across 4 items; 4 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management67
- Stability observed for 20 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage100
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 100% of tool parameters carry a description.Pass
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- We read all 4 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
- An AI judge read all 5 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities60
- Spec-recency check failed: implements MCP spec 2025-06-18; the latest is 2026-07-28. See how to fix → Fail
Unverified: 1 category
A category scored 0 because we could not verify it: a data source with nothing on this package, evidence we could not reach, or a check we could not run. We only credit what we can confirm.
Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.
- 17 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 60 to 63. That category is still filling its 30-day observation window: 18 days of observed history at the previous scan, 19 at this one. The score rises as the window fills, whether or not the server changes.
- 15 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 53 to 57. That category is still filling its 30-day observation window: 16 days of observed history at the previous scan, 17 at this one. The score rises as the window fills, whether or not the server changes.
- 13 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 47 to 50. That category is still filling its 30-day observation window: 14 days of observed history at the previous scan, 15 at this one. The score rises as the window fills, whether or not the server changes.
- 12 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 40 to 47. That category is still filling its 30-day observation window: 12 days of observed history at the previous scan, 14 at this one. The score rises as the window fills, whether or not the server changes.
- 10 Oct 26 +5
- Stability: unverified → 0.40 ▲ functional
- 28 Sept 26 +39
- We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
- 25 Sept 26 −4
- We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
- 26 Aug 26 0
- We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.
Captured 18 Oct 2026 · Analysed mcpb/https://github.com/soren-achebe/backscroll/releases/download/v0.13.1/backscroll-0.13.1.mcpb
Provenance Verified
A signed build attestation was found and verified, binding this exact artifact to the source repository it claims to come from.
| Result | Verified |
|---|---|
| Ecosystem | mcpb |
| Reason | Verified |
| Discovered via | GitHub artifact attestations |
| Source repo | soren-achebe/backscroll |
| Certificate issuer | https://token.actions.githubusercontent.com |
| Certificate SAN | https://github.com/soren-achebe/backscroll/.github/workflows/release.yml@refs/tags/v0.13.1 |
| Rekor log index | 2496477548 |
| Predicate type | SLSA build provenance https://slsa.dev/provenance/v1 |
| Subject digest | sha256:ca59dfeb942d5daf0cadbe5a63897e91c5bcdb40f71f4672fcf8d772d8c7b36f |
Background: How many MCP packages publish verified provenance →
The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →
diff_output Diff two runs' outputs ~177
Unified diff (diff -u style plain text) between the stored outputs of two runs. With only 'id', diffs that command against the most recent EARLIER run of the exact same command line — 'what changed since it last ran?'; errors if no earlier identical command line exists. With 'other', diffs the two given commands (other = older side). Identical outputs return a note saying so. Secrets are masked by default. Read-only: diffs recordings, never re-runs anything.
| Name | Type | Req | Description |
|---|---|---|---|
| context | integer | – | lines of context around changes (default 3) |
| id | integer | yes | newer command id (or -N for Nth most recent; -1 = last command) |
| other | integer | – | older command id to compare against (optional; default: previous run of the same command) |
No output schema declared.
No examples provided.
get_output Get a command's output ~191
Get the full recorded output of one terminal command, plus its command line, exit code, cwd and timing, as plain text (ANSI escapes stripped; secrets masked by default). id: a command id from search_output/list_commands, or negative for relative addressing (-1 = the user's most recent command, -2 = the one before it). Outputs larger than max_bytes return the head and tail around a '[... N bytes omitted ...]' marker — call again with a larger max_bytes for more. Errors with 'not found' if the id doesn't exist. Read-only: reads the recording, never re-runs the command.
| Name | Type | Req | Description |
|---|---|---|---|
| id | integer | yes | command id, or -N for Nth most recent (-1 = last command) |
| max_bytes | integer | – | cap on returned output size (default 51200); if the output is larger, the head and tail are returned with a gap marker |
No output schema declared.
No examples provided.
list_commands List recent commands ~238
List the user's recent terminal commands (most recent first) as plain text: one entry per command with id, time, cwd, exit code, duration and output size — command lines only, no output text. Supports the same filters as search_output, e.g. exit='fail' for recent failures or cwd='.' for this project only. Use this to browse history; use search_output when looking for specific text, and get_output to read what a command actually printed. Read-only: never re-runs anything.
| Name | Type | Req | Description |
|---|---|---|---|
| cwd | string | – | only commands run in this directory or beneath it |
| exit | string | – | only this exit code (a number), or 'fail' for any nonzero |
| host | string | – | only commands from this synced machine ('local' = this machine) |
| limit | integer | – | max results (default 20, max 100) |
| since | string | – | only commands newer than this: 30m, 2h, 3d, 1w, or a date |
| until | string | – | only commands older than this (exclusive; same forms as since) |
No output schema declared.
No examples provided.
search_output Search command outputs ~371
Full-text search over recorded terminal commands, their outputs, and user notes — finds e.g. every command that ever printed 'connection refused'. Returns plain text, one block per match: id, time, cwd, exit code, the command line, and a snippet around the match (secrets are masked by default). Use this to FIND which command said something; use list_commands to browse recent history without a search term, and get_output to read a full output once you have an id. No matches returns an empty result, not an error. Read-only: never re-runs anything.
| Name | Type | Req | Description |
|---|---|---|---|
| context_lines | integer | – | instead of a short snippet, show every matching output line with this many lines of context before and after (grep -C style, with line numbers; 0 = matching lines only, max 10). Often avoids a follow… |
| cwd | string | – | only commands run in this directory or beneath it (absolute path, or '.' for the server's cwd) |
| exit | string | – | only this exit code (a number), or 'fail' for any nonzero |
| host | string | – | only commands from this synced machine ('local' = this machine) |
| limit | integer | – | max results (default 20, max 100) |
| query | string | yes | text to search for in command lines, outputs and notes (substring match; case-insensitive) |
| since | string | – | only commands newer than this: 30m, 2h, 3d, 1w, or 2006-01-02[ 15:04] |
| until | string | – | only commands older than this (exclusive; same forms as since). Combine with since to bound a time window, e.g. one day. |
No output schema declared.
No examples provided.
How do I install the backscroll MCP server?
backscroll ships as an MCPB bundle, a single file you download and open in an MCP host that supports MCPB bundles, such as Claude Desktop. The host reads the launch command from the bundle's own manifest, so there is no command to copy. The MCP registry declares no SHA-256 for this bundle, so there is no published digest to check the download against.
mcpb · backscroll-0.13.1.mcpb
Download bundleThe MCP registry declares no SHA-256 for this bundle, so there is no published digest to check it against. Open it with an MCPB-capable host such as Claude Desktop.
What is the backscroll MCP server?
backscroll is an MCP server listed in the public MCP registry as io.github.soren-achebe/backscroll. Search, retrieve, and diff the full output of past terminal commands recorded locally by backscroll. This page covers its MCPB bundle (https://github.com/soren-achebe/backscroll/releases/download/v0.13.1/backscroll-0.13.1.mcpb).
Is the backscroll MCP server safe to use?
backscroll scores 58 out of 100 on VerifyMCP. Its build provenance is signed and verified. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.
What tools does the backscroll MCP server expose?
backscroll exposes 4 tools: search_output, list_commands, get_output, diff_output. Their descriptions and schemas cost roughly 977 tokens of context every time the server is loaded.
What licence is the backscroll MCP server under?
backscroll declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.