io.github.Jarroslav/agentic-os
NPM · AGENTIC-OS-MCP · SCANNED SEP 20
Read-only, never-executing MCP server for the agentic-os governance, SDLC, and QE methodology.
Available components
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 Security98
- No malware found by supply-chain analysis.Pass
- No known CVEs affecting this package version or its production dependencies.Pass
- No install/post-install scripts declared.Pass
- 31 of 96 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency74
- Repository check failed: no source repository is declared. See how to fix → View diagnostics → Fail
- Cryptographically verified build provenance (signed, bound to Jarroslav/agentic-os). View diagnostics → Pass
- Clear OSI-approved license (Apache-2.0).Pass
- Actively maintained (last published 53 days ago).Pass
- Publishes a security disclosure policy (SECURITY.md).Pass
Schema Quality & AI Usability81
- 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).Pass
- AI-judged instruction clarity (excellent).Pass
- Context-footprint check failed: tool/resource definitions use about 6516 tokens (~171/item across 38 items; 7 tools + 31 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 Management90
- Stability observed for 27 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
- Structured output schemas are declared (100% 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
- We read all 7 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
- An AI judge read all 9 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
- Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
How do I install the io.github.Jarroslav/agentic-os MCP server?
io.github.Jarroslav/agentic-os runs locally as an npm package, launched with npx -y agentic-os-mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
npm · agentic-os-mcp
claude mcp add jarroslav-agentic-os -- npx -y agentic-os-mcp
{
"mcpServers": {
"jarroslav-agentic-os": {
"command": "npx",
"args": [
"-y",
"agentic-os-mcp"
]
}
}
} {
"servers": {
"jarroslav-agentic-os": {
"command": "npx",
"args": [
"-y",
"agentic-os-mcp"
]
}
}
} codex mcp add jarroslav-agentic-os -- npx -y agentic-os-mcp
{
"$schema": "https://opencode.ai/config.json",
"mcp": {
"jarroslav-agentic-os": {
"type": "local",
"command": [
"npx",
"-y",
"agentic-os-mcp"
],
"enabled": true
}
}
} openclaw mcp add jarroslav-agentic-os --command npx --arg -y --arg agentic-os-mcp
mcp_servers:
jarroslav-agentic-os:
command: "npx"
args: ["-y", "agentic-os-mcp"] {
"McpServers": {
"jarroslav-agentic-os": {
"Transport": "stdio",
"Command": "npx",
"Arguments": [
"-y",
"agentic-os-mcp"
]
}
}
} assistant mcp add jarroslav-agentic-os -t stdio -c npx -a -y agentic-os-mcp
{
"mcpServers": {
"jarroslav-agentic-os": {
"command": "npx",
"args": [
"-y",
"agentic-os-mcp"
]
}
}
} 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.
- 19 Sept 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 83 to 87. That category is still filling its 30-day observation window: 25 days of observed history at the previous scan, 26 at this one. The score rises as the window fills, whether or not the server changes.
- 17 Sept 26 −3
- Stability: pass → 0.80 functional
- 16 Sept 26 +1
- Stability: 0.97 → pass security
- 14 Sept 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 90 to 93. That category is still filling its 30-day observation window: 27 days of observed history at the previous scan, 28 at this one. The score rises as the window fills, whether or not the server changes.
- 12 Sept 26 +1
- Security disclosure: unverified → pass ▲ functional
- 11 Sept 26 0
- Security disclosure: pass → unverified ▼ functional
- 10 Sept 26 −3
- Stability: pass → 0.80 functional
- 9 Sept 26 +1
- Stability: 0.97 → pass security
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 20 Sept 2026 · Analysed npm/agentic-os-mcp@0.2.11
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 | npm |
| Reason | Verified |
| Discovered via | Registry attestation endpoint |
| Source repo | Jarroslav/agentic-os |
| Certificate issuer | https://token.actions.githubusercontent.com |
| Certificate SAN | https://github.com/Jarroslav/agentic-os/.github/workflows/release.yml@refs/tags/agentic-os-mcp-v0.2.11 |
| Rekor log index | 2271194981 |
| Predicate type | https://slsa.dev/provenance/v1 |
| Subject digest | sha512:9c6c8ba3f7d6c91d964e6c7bba0ed035eb08403299f8cc8c5d9ee4b73703efdefe0fbaeebc327998dade5c60e07ccdab36b54f9625ae04ed299ab87e5 |
Background: How many MCP packages publish verified provenance →
Dependencies 96 packages
| Packages resolved | 96 |
|---|---|
| Stale | 31 |
| Tree resolution | Complete |
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 →
get_document Get an agentic-os document ~219
Fetch the full text of one agentic-os methodology document, named by its exact agentic-os:// URI. Use it to read a document you have already located — normally via search_methodology, whose every result carries the URI to pass here. It resolves exact URIs only and cannot search, so a guessed URI returns an error rather than a near match. Read-only and idempotent: nothing is ever written, and the same URI returns the same document. A body longer than max_chars comes back cut at a code-point boundary with truncated set and total_chars giving the full length.
| Name | Type | Req | Description |
|---|---|---|---|
| max_chars | integer | – | Truncate the body at this many Unicode code points (not UTF-16 code units — astral-plane characters such as emoji count as one). |
| uri | string | yes | An agentic-os:// URI, e.g. agentic-os://skills/agentic-sdlc/qa-gates or agentic-os://file/agentic-sdlc/agents/guide-sync.md. Get these from search_methodology. |
| Name | Type | Req | Description |
|---|---|---|---|
| text | string | yes | The document body — complete, or cut to max_chars code points when truncated is true. |
| title | string | yes | The document's first markdown heading, or its path within the content bundle when it has no heading. |
| total_chars | number | yes | Length of the complete, untruncated body in Unicode code points — the same unit max_chars is measured in, so total_chars > max_chars is precisely the condition that sets truncated. |
| truncated | boolean | yes | true when the body was cut because it exceeded max_chars. There is no offset or paging parameter: re-request with a larger max_chars to get the rest. |
| uri | string | yes | The requested URI, echoed back unchanged. |
No examples provided.
list_presets List agentic-os role presets ~103
List the agentic-os role presets — the named role bundles (developer, qa, architect, devops, and so on) that decide which governance files an install scaffolds and how much human approval it demands. Use it to discover the valid role names before calling plan_install, or to compare what roles differ on; each entry carries a uri you can read for the preset in full. Takes no arguments and always returns every preset. Read-only and idempotent.
Input schema present but exposes no named parameters.
| Name | Type | Req | Description |
|---|---|---|---|
| presets | array | yes | Every role preset in the bundle, ordered by role name. Never empty in a healthy install — an empty list means the preset directory failed to load and is returned as an error instead. |
No examples provided.
list_qe_blueprints List QE blueprints ~142
Browse the agentic-qe Quality Engineering blueprint catalog, organized by STLC stage. Each blueprint describes how to build one piece of QE capability (test-coverage analysis, flaky-test debugging, and so on); use this to find the blueprint that fits a QE task, then read its uri for the instructions. Returns titles and one-line summaries only — it is a catalog index, not the blueprint content. The stage argument enumerates the valid stages. Read-only and idempotent.
| Name | Type | Req | Description |
|---|---|---|---|
| stage | string | – | Restrict results to a single STLC stage. Omit to return the whole catalog, which is small enough to scan in one call. |
| Name | Type | Req | Description |
|---|---|---|---|
| blueprints | array | yes | Matching blueprints, ordered by stage then id. Empty only when a stage filter matched nothing; an unfiltered call that finds nothing is reported as an error instead, since that means the catalog fail… |
No examples provided.
list_sdlc_phases List SDLC pipeline phases ~107
List the agentic-sdlc pipeline phases in execution order, with each phase's skip condition and the judgment gates it raises — the points where the flow must stop for a human decision. Use it to drive the SDLC flow yourself in a host that cannot run the plugin, or to answer what happens when in the pipeline. Returns the phase and gate skeleton only; read source_uri for what each phase actually does. Takes no arguments. Read-only and idempotent.
Input schema present but exposes no named parameters.
| Name | Type | Req | Description |
|---|---|---|---|
| phases | array | yes | Every pipeline phase, in execution order from phase 0. |
| source_uri | string | yes | URI of the pipeline skill this map was parsed from. Read it with get_document for what each phase actually does — this tool returns only the phase/gate skeleton. |
No examples provided.
plan_install Plan an agentic-os install ~221
Compose one or more agentic-os role presets into an ordered manifest of the files an install should scaffold, each with a uri to read its template from. Use it after list_presets to turn chosen roles into concrete steps. Composition is additive: roles are unioned, the strictest HITL level wins, and every orchestration style in the union is installed. **This returns a plan and writes nothing** — no file is created, and the target repository is neither read nor touched, so the plan is not validated against what may already be installed (use run_doctor for that). You perform every write yourself, so the user can review each one. Read-only and idempotent.
| Name | Type | Req | Description |
|---|---|---|---|
| roles | array | yes | Role preset names to compose, e.g. ["developer","qa"]. At least one is required. Get the valid names from list_presets — an unrecognized name is an error, not a silent skip, and no partial plan is re… |
| Name | Type | Req | Description |
|---|---|---|---|
| files | array | yes | The files to scaffold, ordered by template id. This is the plan's payload: you read each source_uri and perform the writes yourself. Any template with no file in the bundle is reported in follow_ups… |
| follow_ups | array | yes | Problems and decisions this plan could not settle — a missing template, an undeterminable HITL level or orchestration default. Surface these rather than installing past them: an empty array means the… |
| generated_candidates | array | yes | Stack-specific agent contracts this role set *could* generate — candidates, not commitments. Generating one requires facts about the target stack that this server does not have, so filter them agains… |
| hitl_default | string | yes | The human-in-the-loop level to install: the strictest among the chosen roles ("strict" > "gated-autonomous" > "autonomous"). Empty if no role declared a recognized level, in which case follow_ups say… |
| orchestration_default | string | yes | The style to pre-select as active: the first listed role's default, except that a "strict" hitl_default forces "dispatcher". Empty if undeterminable, in which case follow_ups says to set it explicitl… |
| orchestration_installed | array | yes | Every orchestration style to install — the union across roles, not a single choice, because a mixed team needs each one present. |
| roles | array | yes | The roles this plan composes, echoed back in the order given (which determines orchestration_default). |
| sdlc_skills | array | yes | agentic-sdlc pipeline skills the composed roles enable. Empty if no chosen role takes part in the SDLC flow. |
No examples provided.
run_doctor Verify an agentic-os install ~271
Audits an agentic-os install in a target repo you name. Runs the checks that are pure file inspection natively and returns a verdict for each; the three checks that need executing Python (hook compile+import, canned-event dry-runs, HITL smoke) come back as exact commands in host_must_run for you to run yourself — this server never executes code from a target repository, and two of those three commands sets (dry_runs, hitl_smoke) write and then delete a probe file under .agentic/agents/ in the target repo when you run them (see each entry's why). verdict is "passed" only when every native check passed AND host_must_run is empty; it is "incomplete", never "passed", while host_must_run still has entries — which is every install this server finds, since host_must_run is never empty on a single server-side call. This server alone therefore never returns "passed"; that verdict is only reachable once the host has run the returned commands and folded the result back in.
| Name | Type | Req | Description |
|---|---|---|---|
| target_path | string | yes | Filesystem path to the repository to audit — an absolute path, or one resolvable from the host process's working directory. Must already exist and be a directory; this server never creates one. |
| Name | Type | Req | Description |
|---|---|---|---|
| checks | array | yes | Every native (pure file inspection) check this server ran, including "dependencies" — a permanent, structural placeholder that always reports passed: false because verifying installed plugin sources… |
| failures | array | yes | "key: detail" for every entry in checks with passed: false, EXCLUDING "dependencies" — which always reports passed: false but is not a real failure (see checks' description above). An empty failures… |
| host_must_run | array | yes | Command sets for the three checks that require executing Python (hook compile+import, canned-event dry-runs, HITL smoke). Empty when installed is false (nothing to check yet). Non-empty entries here… |
| installed | boolean | yes | Whether .agentic/agentic-os/install.json exists at target_path and parses as JSON. false means none of the checks below ran — checks will contain the single not-installed sentinel instead. |
| verdict | string | yes | "failed": at least one check other than "dependencies" reported passed: false — a real, native-verifiable problem exists in the target repo. "incomplete": every other native check passed, but host_mu… |
No examples provided.
search_methodology Search agentic-os methodology ~284
Full-text search over the agentic-os governance, agentic-sdlc pipeline, and agentic-qe blueprint documentation. Use it first whenever you do not already hold a document URI, then pass a result uri to get_document for the full text. Matching is AND, not OR — every term must appear — and terms match at word starts, so "gate" finds "gates" and "gating" but "ate" finds neither. It searches markdown only: role presets are JSON and never appear here, so use list_presets for those. Read-only and idempotent; searches the server's own bundled corpus, never the network or your repository.
| Name | Type | Req | Description |
|---|---|---|---|
| limit | integer | – | Maximum number of results, best-scoring first (1-25). |
| plugin | string | – | Restrict results to one plugin: agentic-os (governance), agentic-sdlc (the SDLC pipeline), or agentic-qe (QE blueprints). Omit to search all three, which is usually right unless you already know the… |
| query | string | yes | Search terms, e.g. "write scope enforcement". Every term must appear in a document for it to match, so two or three distinctive words find more than a full sentence does. Runs of fewer than two alpha… |
| Name | Type | Req | Description |
|---|---|---|---|
| results | array | yes | Matching documents, best first. Empty when nothing matched — a normal result, not an error; broaden the query or drop the plugin filter. |
No examples provided.
What is the io.github.Jarroslav/agentic-os MCP server?
io.github.Jarroslav/agentic-os is an MCP server listed in the public MCP registry as io.github.Jarroslav/agentic-os. Read-only, never-executing MCP server for the agentic-os governance, SDLC, and QE methodology. This page covers its npm package (agentic-os-mcp).
Is the io.github.Jarroslav/agentic-os MCP server safe to use?
io.github.Jarroslav/agentic-os scores 89 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 20 September 2026. It declares no install or post-install scripts. 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 io.github.Jarroslav/agentic-os MCP server expose?
io.github.Jarroslav/agentic-os exposes 7 tools: search_methodology, get_document, list_presets, list_qe_blueprints, list_sdlc_phases, and 2 more. Their descriptions and schemas cost roughly 1,347 tokens of context every time the server is loaded.
Is the io.github.Jarroslav/agentic-os MCP server still maintained?
io.github.Jarroslav/agentic-os is still listed as active in the MCP registry. We last reached this channel on 20 September 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.Jarroslav/agentic-os MCP server under?
io.github.Jarroslav/agentic-os 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.