io.github.sairam0424/ag-bash
NPM · @AG-BASH/MCP-SERVER
Sandboxed AI-native bash with 70 agentic tools: run_bash, code edit/diff, WASM Python/JS.
Available components
Last scanned (10 hours ago)
Scores higher than 31% of npm 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 Security93
- No malware found by supply-chain analysis.Pass
- CVE check failed: a known medium-severity CVE affects minimatch 10.2.6, reached via @ag-bash/bash > minimatch. A fixed version is available. View diagnostics → Fail
- No install/post-install scripts declared.Pass
- Dependency health was assessed across the 120 of 124 dependencies we could resolve, so this covers what we could see, not the whole tree. View diagnostics → Partial
Provenance & Transparency48
- Source repository is publicly reachable at the declared URL. View diagnostics → Pass
- Provenance check failed: no build-provenance attestation is published. See how to fix → View diagnostics → Fail
- Clear OSI-approved license (Apache-2.0).Pass
- Actively maintained (last published 43 days ago).Pass
- Publishes a security disclosure policy (SECURITY.md).Pass
Schema Quality & AI Usability46
- 2% of prompts and resources have a non-trivial description (not blank, and not just the item's name).Partial
- AI-judged instruction clarity (good).Pass
- Tool/resource definitions use about 5396 tokens (~16/item across 328 items; 70 tools + 258 resources), lean.Pass
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management0
- Stability not yet verified: two runs of the same published version returned different tool surfaces, so we cannot tell a change in the package from a difference in our own sandbox run.Unverified
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
- Structured output schemas are declared (11% of tools); any adoption earns full credit.Pass
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- All 9 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation.Pass
- An AI judge read all 71 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.
Checks we ran (15)
- Malware scan
- Known CVEs
- Install scripts
- Dependency health
- Source repository
- Provenance
- License
- Maintenance
- Security disclosure
- Schema quality
- Tool coverage
- Injection markers
- Destructive annotations
- Judged manipulation
- MCP protocol
Checks we could not complete (1)
These are gaps on our side, not findings about this package. We only credit what we can confirm, so a category made up entirely of them scores 0.
- Stability in Stability & Change Management (scores 0 for this)Stability not yet verified: two runs of the same published version returned different tool surfaces, so we cannot tell a change in the package from a difference in our own sandbox run.
Does not apply to this package (2)
- Endpoint SecurityScored on hosted endpoints only. A package has no live endpoint of its own for us to probe.
- Transport & ReachabilityScored on hosted endpoints only. A package has no live endpoint of its own for us to probe.
The score does not measure everything. What the score does not measure →
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.
- 31 Oct 26 −1
- CVE-2026-118764 affects this package: medium ▼ security
- Known CVEs: partial → fail ▼ security
- 23 Oct 26 0
- CVE-2026-97058 no longer affects this package ▲ security
- Known CVEs: Known CVEs were checked across the 126 of 130 dependencies we could resolve, so this covers what we could see, not the whole tree. security
- 11 Oct 26 0
- CVE-2026-97058 affects this package ▼ security
- Known CVEs: A known CVE affects sprintf-js, but no fixed version has been published, so there is nothing to upgrade to. security
- 28 Sept 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
- 25 Sept 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
- 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
- 13 Aug 26 0
- Security disclosure: unverified → pass ▲ functional
- 12 Aug 26 0
- Security disclosure: pass → unverified ▼ 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 7 Nov 2026 · Analysed npm/@ag-bash/mcp-server@6.0.4
Provenance No attestation
The registry publishes no build provenance for this version, so there is nothing to verify.
| Result | No attestation |
|---|---|
| Ecosystem | npm |
Background: How many MCP packages publish verified provenance →
Vulnerabilities 1 finding
| ID | CVE | Severity | Vector | Fix available |
|---|---|---|---|---|
| GHSA-g3hv-75wg-m249 | CVE-2026-118764 | medium | yes |
Background: What a vulnerability scan can and cannot prove →
Dependencies 120 packages
| Packages resolved | 120 |
|---|---|
| Deprecated | 1 |
| Stale | 40 |
| Tree resolution | Partial |
The dependency tree was only partially resolved, so these counts may be incomplete.
Background: SBOMs and build attestations, explained →
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 →
run_bash ~44
Run a bash script in a persistent sandboxed environment. State (cwd, variables, functions) persists between calls.
| Name | Type | Req | Description |
|---|---|---|---|
| script | string | yes | The bash script to execute. |
| Name | Type | Req | Description |
|---|---|---|---|
| exitCode | number | yes | Process exit code (0 = success). |
| stderr | string | yes | Standard error captured from the script. |
| stdout | string | yes | Standard output captured from the script. |
No examples provided.
run_command ~28
Execute a shell command in the sandbox.
| Name | Type | Req | Description |
|---|---|---|---|
| command | string | yes | The shell command to execute. |
No output schema declared.
No examples provided.
run_js ~37
Execute JavaScript code in the sandbox. For persistent state, use run_js_session.
| Name | Type | Req | Description |
|---|---|---|---|
| code | string | yes | The JS code to execute. |
No output schema declared.
No examples provided.
run_js_session ~62
Execute JavaScript code in a persistent session (stateful REPL). Maintains variables and modules between calls.
| Name | Type | Req | Description |
|---|---|---|---|
| code | string | yes | The JS code to execute. |
| sessionId | string | yes | Session identifier (e.g., 'main', 'test'). |
No output schema declared.
No examples provided.
run_python ~36
Execute Python code in the sandbox. For persistent state, use run_python_session.
| Name | Type | Req | Description |
|---|---|---|---|
| code | string | yes | The Python code to execute. |
No output schema declared.
No examples provided.
run_python_session ~59
Execute Python code in a persistent session (stateful REPL). Maintains variables and imports between calls.
| Name | Type | Req | Description |
|---|---|---|---|
| code | string | yes | The Python code to execute. |
| sessionId | string | yes | Session identifier (e.g., 'data-analysis'). |
No output schema declared.
No examples provided.
search_tools ~85
Discover which agentic tools are available for a free-text task description (Code Mode). Returns the best-matching tools by relevance so an agent can pick a tool without pre-loading the full catalog.
| Name | Type | Req | Description |
|---|---|---|---|
| limit | number | – | Maximum number of matches to return (1-25, default 5). |
| query | string | yes | Free-text description of the task or capability you need. |
| Name | Type | Req | Description |
|---|---|---|---|
| matches | array | yes | Matching tools, best first. |
| query | string | yes | The query that was searched. |
No examples provided.
search_tools ~66
Search for available tools by keyword, or select by exact name with 'select:Name1,Name2'.
| Name | Type | Req | Description |
|---|---|---|---|
| limit | number | – | Max results (default: 10). |
| query | string | yes | Keyword query or "select:Name1,Name2" for exact lookup. |
No output schema declared.
No examples provided.
send_message ~46
Send a message from one agent to another.
| Name | Type | Req | Description |
|---|---|---|---|
| content | string | yes | Message content. |
| from | string | yes | Sender agent ID. |
| to | string | yes | Recipient agent ID. |
No output schema declared.
No examples provided.
snapshot ~22
Capture a complete binary snapshot of the current shell state (filesystem + environment).
Input schema present but exposes no named parameters.
| Name | Type | Req | Description |
|---|---|---|---|
| encoded | string | yes | Base64-encoded opaque state blob. |
No examples provided.
sync_mcp_tools ~22
Synchronize and register all MCP tools into the central toolbox.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
task_create ~81
Create a new tracked task with subject, description, owner, and progress text.
| Name | Type | Req | Description |
|---|---|---|---|
| activeForm | string | – | Spinner text when in_progress (e.g., "Running tests"). |
| description | string | yes | What needs to be done. |
| owner | string | – | Agent ID that owns this task. |
| subject | string | yes | Brief title for the task. |
No output schema declared.
No examples provided.
task_get ~29
Get full details of a specific task by ID.
| Name | Type | Req | Description |
|---|---|---|---|
| taskId | string | yes | The task ID. |
No output schema declared.
No examples provided.
task_list ~42
List all tracked tasks, optionally filtered by status or owner.
| Name | Type | Req | Description |
|---|---|---|---|
| owner | string | – | Filter by owner agent ID. |
| status | string | – | Filter by status. |
No output schema declared.
No examples provided.
task_stop ~29
Stop (fail) a running task.
| Name | Type | Req | Description |
|---|---|---|---|
| taskId | string | yes | The task ID to stop. |
No output schema declared.
No examples provided.
task_update ~114
Update a task's status, subject, description, owner, or dependencies.
| Name | Type | Req | Description |
|---|---|---|---|
| addBlockedBy | string | – | Task IDs that block this task. |
| addBlocks | string | – | Task IDs that this task blocks. |
| description | string | – | New description. |
| owner | string | – | New owner agent ID. |
| status | string | – | New status: pending, in_progress, completed, failed, blocked. |
| subject | string | – | New subject. |
| taskId | string | yes | The task ID to update. |
No output schema declared.
No examples provided.
team_create ~37
Create a new agent team for coordinated multi-agent work.
| Name | Type | Req | Description |
|---|---|---|---|
| description | string | – | Team purpose. |
| name | string | yes | Team name. |
No output schema declared.
No examples provided.
team_delete ~24
Delete an agent team.
| Name | Type | Req | Description |
|---|---|---|---|
| name | string | yes | Team name or ID. |
No output schema declared.
No examples provided.
update_todo ~40
Update the status of a todo item.
| Name | Type | Req | Description |
|---|---|---|---|
| id | string | yes | The ID of the todo to update. |
| status | string | yes | New status. |
No output schema declared.
No examples provided.
write_file ~46
Create or overwrite a file in the virtual filesystem.
| Name | Type | Req | Description |
|---|---|---|---|
| content | string | yes | The content to write to the file. |
| path | string | yes | Absolute path to the file to write. |
No output schema declared.
No examples provided.
How do I install the io.github.sairam0424/ag-bash MCP server?
io.github.sairam0424/ag-bash runs locally as an npm package, launched with npx -y @ag-bash/mcp-server. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
npm · @ag-bash/mcp-server
claude mcp add sairam0424-ag-bash -- npx -y @ag-bash/mcp-server
What is the io.github.sairam0424/ag-bash MCP server?
io.github.sairam0424/ag-bash is an MCP server listed in the public MCP registry as io.github.sairam0424/ag-bash. Sandboxed AI-native bash with 70 agentic tools: run_bash, code edit/diff, WASM Python/JS. This page covers its npm package (@ag-bash/mcp-server).
Is the io.github.sairam0424/ag-bash MCP server safe to use?
io.github.sairam0424/ag-bash scores 62 out of 100 on VerifyMCP. We recorded 1 known advisory against it as of 7 November 2026. It declares no install or post-install scripts. 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 io.github.sairam0424/ag-bash MCP server expose?
io.github.sairam0424/ag-bash exposes 70 tools: run_bash, get_state, snapshot, restore, create_delta, and 65 more. Their descriptions and schemas cost roughly 3,444 tokens of context every time the server is loaded.
Is the io.github.sairam0424/ag-bash MCP server still maintained?
io.github.sairam0424/ag-bash is still listed as active in the MCP registry. We last reached this channel on 7 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.
What licence is the io.github.sairam0424/ag-bash MCP server under?
io.github.sairam0424/ag-bash declares the Apache-2.0 licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.
What did VerifyMCP test on the io.github.sairam0424/ag-bash MCP server?
VerifyMCP ran 15 checks on io.github.sairam0424/ag-bash, covering Malware scan, Known CVEs, Install scripts, Dependency health and 11 more. One item could not be completed, a gap on our side rather than a finding about io.github.sairam0424/ag-bash: Stability. One category scores 0 for that reason, because we only credit what we can confirm. Endpoint Security and Transport & Reachability do not apply to an npm package, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.