io.github.HMAKT99/akf
PYPI · MCP-SERVER-AKF
Trust metadata for AI agents — check files before building on them, stamp verified work.
Available components
Last scanned (13 hours ago)
Scores higher than 61% of PyPI servers
Category Security
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 Security50
- Malware scan not yet available for this package.Unverified
- No known CVEs affecting this package version or its production dependencies.Pass
- Runs setuptools.build_meta at install time, a recognised build step with no custom scripting around it. View diagnostics → Pass
- 1 of 29 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency45
- Source repository is publicly reachable at the declared URL. View diagnostics → Pass
- Build provenance not yet verified. View diagnostics → Unverified
- Clear OSI-approved license (MIT).Pass
- Actively maintained (last published 27 days ago).Pass
- Security-disclosure policy not yet verified: we couldn't inspect the source repository.Unverified
Schema Quality & AI Usability74
- AI-judged instruction clarity (good).Pass
- Tool/resource definitions use about 913 tokens (~83/item across 11 items; 11 tools + 0 resources), lean.Pass
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management93
- Stability observed for 28 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 11 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
- An AI judge read all 11 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
- Implements a current MCP spec version (2026-07-28).Pass
Checks we ran (13)
- Known CVEs
- Install scripts
- Dependency health
- Source repository
- License
- Maintenance
- Schema quality
- Stability
- Tool coverage
- Injection markers
- Destructive annotations
- Judged manipulation
- MCP protocol
Checks we could not complete (3)
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.
- Malware scan in Supply Chain SecurityMalware scan not yet available for this package.
- Provenance in Provenance & TransparencyBuild provenance not yet verified.
- Security disclosure in Provenance & TransparencySecurity-disclosure policy not yet verified: we couldn't inspect the source repository.
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.
- 21 Nov 26 0
- Provenance: fail → unverified ▼ security
- Security disclosure: fail → unverified ▼ functional
- 19 Nov 26 −14
- Malware scan: pass → unverified ▼ security
- Package version: 1.6.0 → 1.6.2 functional
- 17 Nov 26 +16
- Malware scan: unverified → pass ▲ security
- 15 Nov 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 70 to 73. That category is still filling its 30-day observation window: 21 days of observed history at the previous scan, 22 at this one. The score rises as the window fills, whether or not the server changes.
- 14 Nov 26 −15
- Malware scan: pass → unverified ▼ security
- 13 Nov 26 +16
- Malware scan: unverified → pass ▲ security
- 12 Nov 26 −15
- Malware scan: pass → unverified ▼ security
- 11 Nov 26 +16
- Malware scan: unverified → 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 21 Nov 2026 · Analysed pypi/mcp-server-akf@1.6.2
Provenance Inconclusive
We could not complete the check, so nothing is claimed either way. This is a gap on our side, not a finding about the package.
| Result | Inconclusive |
|---|---|
| Ecosystem | pypi |
| Reason | Attestation not fetched |
Background: How many MCP packages publish verified provenance →
Install scripts 1 script
| Hook | Tier | Command |
|---|---|---|
| build_backend | Known build tool | setuptools.build_meta |
Background: Why install scripts are a supply-chain risk →
Dependencies 29 packages
| Packages resolved | 29 |
|---|---|
| No linked repository | 1 |
| 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 →
audit_file ~90
Run compliance audit on an AKF file against regulatory frameworks (EU AI Act, SOX, HIPAA, GDPR, NIST AI RMF, ISO 42001).
| Name | Type | Req | Description |
|---|---|---|---|
| path | string | yes | Path to the .akf file to audit |
| regulation | string | – | Target regulation: eu_ai_act, sox, hipaa, gdpr, nist_ai, iso_42001 |
No output schema declared.
No examples provided.
check_file ~107
One-line trust check before building on a file. Returns OK (fresh stamp, trust above threshold — skip re-verification), LOW (trust below threshold), STALE (modified after stamping or claims expired — re-verify), or UNSTAMPED (no metadata). Use this before re-reading, re-testing, or re-deriving work another agent already verified.
| Name | Type | Req | Description |
|---|---|---|---|
| path | string | yes | Path to the file to check |
| threshold | number | – | Trust threshold for OK vs LOW |
No output schema declared.
No examples provided.
create_claim ~92
Create an AKF claim with trust metadata. Returns a JSON object with the claim, trust score, and provenance.
| Name | Type | Req | Description |
|---|---|---|---|
| ai_generated | boolean | – | Whether this claim is AI-generated |
| confidence | number | yes | Trust score 0.0-1.0 |
| content | string | yes | The factual claim to create |
| source | string | – | Information source (e.g., 'SEC 10-Q') |
No output schema declared.
No examples provided.
detect_threats ~56
Run 10 AI-specific security detections on an AKF file: hallucination risk, knowledge laundering, classification downgrade, trust degradation, and more.
| Name | Type | Req | Description |
|---|---|---|---|
| path | string | yes | Path to the .akf file to analyze |
No output schema declared.
No examples provided.
embed_file ~86
Embed AKF trust metadata into any supported file format (DOCX, PDF, HTML, images, Markdown, etc.).
| Name | Type | Req | Description |
|---|---|---|---|
| classification | string | – | Security classification |
| confidence | number | – | Confidence score |
| content | string | yes | The factual claim to embed |
| path | string | yes | Path to the file to embed metadata into |
| source | string | – | Information source |
No output schema declared.
No examples provided.
extract_file ~45
Extract AKF trust metadata from any supported file format. Returns claims, classification, provenance, and trust scores.
| Name | Type | Req | Description |
|---|---|---|---|
| path | string | yes | Path to the file to extract metadata from |
No output schema declared.
No examples provided.
replay_file ~116
Replay-verify a stamp's falsifiable probe recipe. Default inspects only: shows the recorded command and whether the claim's inputs drifted since issuance. With run=true, EXECUTES the recorded command (arbitrary code — only for files you trust) and returns CONFIRMED / CONFIRMED_DRIFTED (succeeded against diverged inputs) / REFUTED / UNREPLAYABLE.
| Name | Type | Req | Description |
|---|---|---|---|
| path | string | yes | Path to the stamped file |
| run | boolean | – | Execute the recorded command (review it first) |
No output schema declared.
No examples provided.
scan_file ~63
Security scan any file for AKF trust metadata. Works with .akf, .docx, .pdf, .html, .md, .json, images, and any format with a sidecar.
| Name | Type | Req | Description |
|---|---|---|---|
| path | string | yes | Path to the file to scan |
No output schema declared.
No examples provided.
stamp_file ~124
Stamp AKF trust metadata onto any file. Supports DOCX, PDF, images, Markdown, code, and 20+ formats. Use this after creating or modifying files.
| Name | Type | Req | Description |
|---|---|---|---|
| agent | string | – | Agent identity (e.g., 'claude-code', 'copilot') |
| classification | string | – | Security classification: public, internal, confidential, restricted |
| confidence | number | – | Confidence score |
| evidence | string | – | Comma-separated evidence (e.g., 'tests pass, docs reviewed') |
| path | string | yes | Path to the file to stamp |
No output schema declared.
No examples provided.
trust_score ~82
Compute the effective trust score for a claim using AKF's trust computation engine. Factors in confidence, authority tier, and temporal decay.
| Name | Type | Req | Description |
|---|---|---|---|
| authority_tier | integer | – | Authority tier 1-5 (1=official records, 5=AI inference) |
| confidence | number | yes | Base confidence score |
| content | string | yes | The claim to score |
No output schema declared.
No examples provided.
validate_file ~52
Validate an .akf file against the AKF specification. Returns validity status, validation level (0-3), errors, and warnings.
| Name | Type | Req | Description |
|---|---|---|---|
| path | string | yes | Path to the .akf file to validate |
No output schema declared.
No examples provided.
How do I install the io.github.HMAKT99/akf MCP server?
io.github.HMAKT99/akf runs locally as a PyPI package, launched with uvx mcp-server-akf. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
pypi · mcp-server-akf
claude mcp add hmakt99-akf -- uvx mcp-server-akf
What is the io.github.HMAKT99/akf MCP server?
io.github.HMAKT99/akf is an MCP server listed in the public MCP registry as io.github.HMAKT99/akf. Trust metadata for AI agents, check files before building on them, stamp verified work. This page covers its PyPI package (mcp-server-akf).
Is the io.github.HMAKT99/akf MCP server safe to use?
io.github.HMAKT99/akf scores 68 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 21 November 2026. 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.HMAKT99/akf MCP server expose?
io.github.HMAKT99/akf exposes 11 tools: replay_file, check_file, create_claim, validate_file, scan_file, and 6 more. Their descriptions and schemas cost roughly 913 tokens of context every time the server is loaded.
Is the io.github.HMAKT99/akf MCP server still maintained?
io.github.HMAKT99/akf is still listed as active in the MCP registry. We last reached this channel on 21 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.HMAKT99/akf MCP server under?
io.github.HMAKT99/akf declares the MIT 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.HMAKT99/akf MCP server?
VerifyMCP ran 13 checks on io.github.HMAKT99/akf, covering Known CVEs, Install scripts, Dependency health, Source repository and 9 more. 3 items could not be completed, a gap on our side rather than a finding about io.github.HMAKT99/akf: Malware scan, Provenance and Security disclosure. Endpoint Security and Transport & Reachability do not apply to a PyPI package, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.