io.github.agntcy/dir-mcp
OCI · GHCR.IO/AGNTCY/DIR-MCP:1.3.4 · 2 COMPONENTS · SCANNED SEP 20
MCP server for working with OASF agent records in the Agntcy Directory.
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 Security0
- Malware scan not yet available for this package.Unverified
- Known CVEs could not be checked: this artifact ships no SBOM, so there is no dependency list to read. Publishing one would let us assess it.Unverified
- Install-script risk not yet assessed.Unverified
- Dependency health could not be checked: this artifact ships no SBOM, so there is no dependency list to read. Publishing one would let us assess it.Unverified
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 52 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 2493 tokens (~207/item across 12 items; 12 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 Management83
- Stability observed for 25 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 12 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
- An AI judge read all 12 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
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.
How do I install the io.github.agntcy/dir-mcp server?
io.github.agntcy/dir-mcp runs locally as a container image, launched with docker run --rm -i ghcr.io/agntcy/dir-mcp:1.3.4. Ready-made configuration for Claude, Cursor, VS Code, Codex and 3 more is on this page, copied from each client's own documentation.
oci · ghcr.io/agntcy/dir-mcp:1.3.4
claude mcp add agntcy-dir-mcp -- docker run --rm -i ghcr.io/agntcy/dir-mcp:1.3.4
{
"mcpServers": {
"agntcy-dir-mcp": {
"command": "docker",
"args": [
"run",
"--rm",
"-i",
"ghcr.io/agntcy/dir-mcp:1.3.4"
]
}
}
} {
"servers": {
"agntcy-dir-mcp": {
"command": "docker",
"args": [
"run",
"--rm",
"-i",
"ghcr.io/agntcy/dir-mcp:1.3.4"
]
}
}
} codex mcp add agntcy-dir-mcp -- docker run --rm -i ghcr.io/agntcy/dir-mcp:1.3.4
{
"$schema": "https://opencode.ai/config.json",
"mcp": {
"agntcy-dir-mcp": {
"type": "local",
"command": [
"docker",
"run",
"--rm",
"-i",
"ghcr.io/agntcy/dir-mcp:1.3.4"
],
"enabled": true
}
}
} mcp_servers:
agntcy-dir-mcp:
command: "docker"
args: ["run", "--rm", "-i", "ghcr.io/agntcy/dir-mcp:1.3.4"] {
"McpServers": {
"agntcy-dir-mcp": {
"Transport": "stdio",
"Command": "docker",
"Arguments": [
"run",
"--rm",
"-i",
"ghcr.io/agntcy/dir-mcp:1.3.4"
]
}
}
} {
"mcpServers": {
"agntcy-dir-mcp": {
"command": "docker",
"args": [
"run",
"--rm",
"-i",
"ghcr.io/agntcy/dir-mcp:1.3.4"
]
}
}
} 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.
- 20 Sept 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 80 to 83. That category is still filling its 30-day observation window: 24 days of observed history at the previous scan, 25 at this one. The score rises as the window fills, whether or not the server changes.
- 19 Sept 26 −3
- Stability: pass → 0.80 functional
- 18 Sept 26 0
- Stability: 0.97 → pass security
- 17 Sept 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 93 to 97. That category is still filling its 30-day observation window: 28 days of observed history at the previous scan, 29 at this one. The score rises as the window fills, whether or not the server changes.
- 15 Sept 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 87 to 90. That category is still filling its 30-day observation window: 26 days of observed history at the previous scan, 27 at this one. The score rises as the window fills, whether or not the server changes.
- 13 Sept 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 80 to 83. That category is still filling its 30-day observation window: 24 days of observed history at the previous scan, 25 at this one. The score rises as the window fills, whether or not the server changes.
- 12 Sept 26 −3
- Stability: pass → 0.80 functional
- 11 Sept 26 0
- 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 oci/ghcr.io/agntcy/dir-mcp:1.3.4
Provenance No attestation
The registry publishes no build provenance for this version, so there is nothing to verify.
| Result | No attestation |
|---|---|
| Ecosystem | oci |
| Reason | No attestation published |
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 →
agntcy_dir_pull_record ~94
Pulls an OASF agent record from the local Directory node by its CID (Content Identifier). The pulled record is content-addressable and can be validated against its hash. Server configuration is set via environment variables (DIRECTORY_CLIENT_SERVER_ADDRESS). Use this tool to retrieve agent records by their CID for inspection or validation.
| Name | Type | Req | Description |
|---|---|---|---|
| cid | string | yes | Content Identifier (CID) of the record to pull (required) |
| Name | Type | Req | Description |
|---|---|---|---|
| error_message | string | – | Error message if pull failed |
| record_data | string | – | The record data (JSON string) |
No examples provided.
agntcy_dir_push_record ~119
Pushes an OASF agent record to a Directory server. This tool validates and uploads the record to the configured Directory server, returning: - Content Identifier (CID) for the pushed record - Server address where the record was stored The record must be a valid OASF agent record. Server configuration is set via environment variables (DIRECTORY_CLIENT_SERVER_ADDRESS). Use this tool after validating your record to store it in the Directory.
| Name | Type | Req | Description |
|---|---|---|---|
| record_json | string | yes | JSON string of the OASF agent record to push to Directory server |
| Name | Type | Req | Description |
|---|---|---|---|
| cid | string | – | Content identifier (CID) of the pushed record |
| error_message | string | – | Error message if push failed |
| server_address | string | – | Directory server address where the record was pushed |
No examples provided.
agntcy_dir_search_local ~435
Searches for agent records on the local directory node using structured query filters. This tool supports flexible wildcard patterns for matching records based on: - Agent names (e.g., "gpt*", "agent-?", "web-*") - Versions (e.g., "v1.*", "*-beta", "v?.0.?") - Skill IDs (exact match only, e.g., "10201") - Skill names (e.g., "*python*", "Image*") - Locators (e.g., "docker-image:*", "http*") - Modules (e.g., "*-plugin", "core*") Multiple filters are combined with OR logic (matches any filter). Results are streamed and paginated for efficient handling of large result sets. Server configuration is set via environment variables (DIRECTORY_CLIENT_SERVER_ADDRESS). Use this tool for direct, structured searches when you know the exact filters to apply.
| Name | Type | Req | Description |
|---|---|---|---|
| authors | array | – | Author name patterns (supports wildcards: * ? []) |
| created_ats | array | – | Created_at timestamp patterns (supports wildcards: * ? []) |
| domain_ids | array | – | Domain ID patterns (exact match only) |
| domain_names | array | – | Domain name patterns (supports wildcards: * ? []) |
| limit | integer | – | Maximum number of results to return (default: 100 max: 1000) |
| locators | array | – | Locator patterns (supports wildcards: * ? []) |
| module_ids | array | – | Module ID patterns (exact match only) |
| module_names | array | – | Module name patterns (supports wildcards: * ? []) |
| names | array | – | Agent name patterns (supports wildcards: * ? []) |
| offset | integer | – | Pagination offset (default: 0) |
| schema_versions | array | – | Schema version patterns (supports wildcards: * ? []) |
| skill_ids | array | – | Skill ID patterns (exact match only) |
| skill_names | array | – | Skill name patterns (supports wildcards: * ? []) |
| versions | array | – | Version patterns (supports wildcards: * ? []) |
| Name | Type | Req | Description |
|---|---|---|---|
| count | integer | yes | Number of results returned |
| error_message | string | – | Error message if search failed |
| has_more | boolean | yes | Whether more results are available beyond the limit |
| record_cids | null|array | – | Array of matching record CIDs |
No examples provided.
agntcy_dir_verify_name ~244
Verifies that a record's name is owned by the domain it claims. This tool checks that the record was signed with a key published in the domain's well-known JWKS file (/.well-known/jwks.json). You can verify by: - CID: Directly verify a specific record by its Content Identifier - Name: Verify a record by its human-readable name (e.g., "example.com/my-agent") - Name + Version: Verify a specific version (e.g., "example.com/my-agent" + "v1.0.0") Returns verification status and domain verification details including: - The verified domain - The verification method used - The matched key ID from the domain's JWKS Use this tool to verify that an agent record was actually published by the domain owner.
| Name | Type | Req | Description |
|---|---|---|---|
| cid | string | – | Content Identifier (CID) of the record to verify |
| name | string | – | Human-readable name of the record (e.g., 'example.com/my-agent') |
| version | string | – | Optional version to verify (e.g., 'v1.0.0'). If omitted, verifies the latest version. |
| Name | Type | Req | Description |
|---|---|---|---|
| domain_verification | null|object | – | Details about the domain verification (only present if verified) |
| error_message | string | – | Error message if verification failed |
| verified | boolean | yes | Whether the name ownership was verified |
No examples provided.
agntcy_dir_verify_record ~88
Verifies the digital signature of a record in the Directory by its CID. This tool performs a server-side verification of the record's integrity and authenticity. Returns the verification status (trusted/not trusted). Use this tool to ensure a record has been properly signed and hasn't been tampered with.
| Name | Type | Req | Description |
|---|---|---|---|
| cid | string | yes | Content Identifier (CID) of the record to verify (required) |
| Name | Type | Req | Description |
|---|---|---|---|
| error | string | – | Error message if verification request failed |
| message | string | yes | Status message indicating trust level |
| signers | null|array | – | Information about verified signers |
| success | boolean | yes | Whether the signature verification was successful |
No examples provided.
agntcy_oasf_export_record ~252
Exports an OASF agent record to a different format using the OASF SDK translator. This tool takes an OASF record in JSON format and converts it to the specified target format. Currently supported target formats: - "a2a": Agent-to-Agent (A2A) format - "ghcopilot": GitHub Copilot MCP configuration format - "agentskills": Agent Skills SKILL.md markdown format **Input Format**: Provide the OASF record as a standard JSON object (no wrapper needed). **Output Format**: The output structure depends on the target format: - For "a2a": Returns the A2A card directly as a JSON object - For "ghcopilot": Returns the GitHub Copilot MCP configuration as a JSON object - For "agentskills": Returns a SKILL.md markdown document as plain text Use this tool when you need to convert OASF records to other format specifications.
| Name | Type | Req | Description |
|---|---|---|---|
| record_json | string | yes | JSON string of the OASF agent record to export (required) |
| target_format | string | yes | Target format to export to (a2a, ghcopilot, agentskills) (required) |
| Name | Type | Req | Description |
|---|---|---|---|
| error_message | string | – | Error message if export failed |
| exported_data | string | – | The exported data in the target format (JSON string) |
No examples provided.
agntcy_oasf_get_schema ~123
Retrieves the complete OASF schema JSON content for the specified version. This tool provides direct access to the full schema definition including: - All domain definitions and their IDs - All skill definitions and their IDs - Complete validation rules and constraints - Schema structure and required fields Use this tool to get the complete schema for reference when creating or validating agent records.
| Name | Type | Req | Description |
|---|---|---|---|
| version | string | yes | OASF schema version to retrieve (e.g., 0.7.0, 0.8.0, 1.0.0) |
| Name | Type | Req | Description |
|---|---|---|---|
| available_versions | null|array | – | List of available OASF schema versions |
| error_message | string | yes | Err or message if schema retrieval failed |
| schema | string | yes | The complete OASF schema JSON content |
| version | string | yes | The requested OASF schema version |
No examples provided.
agntcy_oasf_get_schema_domains ~204
Retrieves domains from the OASF schema for the specified version. This tool supports hierarchical domain navigation: - Without parent_domain: Returns all top-level domain categories (e.g., "artificial_intelligence", "software_development") - With parent_domain: Returns sub-domains under that parent (e.g., parent="artificial_intelligence" returns its children) Each domain includes: - name: The domain identifier used in OASF records - caption: Human-readable display name - id: Numeric domain identifier Use this tool to discover valid domains when creating or enriching agent records. Essential for LLM-based enrichment to ensure domains match the schema taxonomy.
| Name | Type | Req | Description |
|---|---|---|---|
| parent_domain | string | – | Optional parent domain name to filter sub-domains (e.g., 'artificial_intelligence') |
| version | string | yes | OASF schema version to retrieve domains from (e.g., 0.7.0, 0.8.0) |
| Name | Type | Req | Description |
|---|---|---|---|
| available_versions | null|array | – | List of available OASF schema versions |
| domains | null|array | yes | List of domains (top-level or filtered by parent) |
| error_message | string | – | Error message if domain retrieval failed |
| parent_domain | string | – | The parent domain filter if specified |
| version | string | yes | The requested OASF schema version |
No examples provided.
agntcy_oasf_get_schema_skills ~207
Retrieves skills from the OASF schema for the specified version. This tool supports hierarchical skill navigation: - Without parent_skill: Returns all top-level skill categories (e.g., "analytical_skills", "natural_language_processing") - With parent_skill: Returns sub-skills under that parent (e.g., parent="retrieval_augmented_generation" returns its children) Each skill includes: - name: The skill identifier used in OASF records - caption: Human-readable display name - id: Numeric skill identifier Use this tool to discover valid skills when creating or enriching agent records. Essential for LLM-based enrichment to ensure skills match the schema taxonomy.
| Name | Type | Req | Description |
|---|---|---|---|
| parent_skill | string | – | Optional parent skill name to filter sub-skills (e.g., 'retrieval_augmented_generation') |
| version | string | yes | OASF schema version to retrieve skills from (e.g., 0.7.0, 0.8.0) |
| Name | Type | Req | Description |
|---|---|---|---|
| available_versions | null|array | – | List of available OASF schema versions |
| error_message | string | – | Error message if skill retrieval failed |
| parent_skill | string | – | The parent skill filter if specified |
| skills | null|array | yes | List of skills (top-level or filtered by parent) |
| version | string | yes | The requested OASF schema version |
No examples provided.
agntcy_oasf_import_record ~559
Imports data from a different format to an OASF agent record using the OASF SDK translator. This tool takes data in a source format and converts it to OASF record format. Currently supported source formats: - "mcp": Model Context Protocol format - "a2a": Agent-to-Agent (A2A) format - "agentskills": Agent Skills SKILL.md markdown format **CRITICAL - Input Format Requirements**: For "mcp" format, provide source_data as: { "server": { "name": "example-server", "version": "1.0.0", ... (rest of MCP server data) } } For "a2a" format, provide source_data as either: 1) wrapped object: { "a2aCard": { "name": "example-agent", "version": "1.0.0", "description": "...", ... (rest of A2A card data) } } 2) or direct A2A card object. For "agentskills" format, provide source_data as a JSON object with a "skillMarkdown" field: { "skillMarkdown": "---\nname: my-skill\ndescription: ...\n---\n\nBody..." } **Important - Enrichment Required**: The domains and skills in the resulting OASF record from the oasf-sdk translator are incomplete and MUST be enriched. Follow these steps: 1. Remove any existing domains and skills fields from the imported record 2. Use agntcy_oasf_get_schema_domains to discover valid domain options: - First get top-level domains (without parent_domain parameter) - Then explore sub-domains using the parent_domain parameter if needed 3. Use agntcy_oasf_get_schema_skills to discover valid skill options: - First get top-level skill categories (without parent_skill parameter) - Then explore sub-skills using the parent_skill parameter if needed 4. Analyze the source content to select the most relevant domains and skills 5. Add the selected domains and skills to the record with proper names and IDs Use this tool when you need to convert records from other format specifications to OASF. For a complete guided workflow including enrichment and validation, use the import_record prompt.
| Name | Type | Req | Description |
|---|---|---|---|
| source_data | string | yes | Source data to import as JSON string (mcp wrapper {server:{...}}, a2a card object/wrapper, or agentskills wrapper {skillMarkdown:"..."}) (required) |
| source_format | string | yes | Source format to import from (mcp, a2a, agentskills) (required) |
| Name | Type | Req | Description |
|---|---|---|---|
| error_message | string | – | Error message if import failed |
| record_json | string | – | The imported OASF record (JSON string) |
No examples provided.
agntcy_oasf_list_versions ~65
Lists all available OASF schema versions supported by the server. This tool provides a simple way to discover what schema versions are available without having to make requests with specific version numbers. Use this tool to see what OASF schema versions you can work with.
Input schema present but exposes no named parameters.
| Name | Type | Req | Description |
|---|---|---|---|
| available_versions | null|array | yes | List of available OASF schema versions |
| count | integer | yes | Number of available schema versions |
| default_version | string | yes | The default OASF schema version |
| error_message | string | – | Error message if version listing failed |
No examples provided.
agntcy_oasf_validate_record ~103
Validates an AGNTCY OASF agent record against the OASF schema. This tool performs comprehensive validation including: - Required fields check - Field type validation - Schema-specific constraints - Domain and skill taxonomy validation Returns detailed validation errors to help fix issues. Use this tool to ensure a record meets all OASF requirements before pushing.
| Name | Type | Req | Description |
|---|---|---|---|
| record_json | string | yes | JSON string of the agent record to validate against OASF schema |
| Name | Type | Req | Description |
|---|---|---|---|
| error_message | string | – | General error message if validation process failed |
| schema_version | string | – | Detected OASF schema version (e.g. 0.7.0, 0.8.0, or 1.0.0) |
| valid | boolean | yes | Whether the record is valid according to OASF schema validation |
| validation_errors | null|array | – | List of validation error messages. Only present if valid=false. Use these to fix the record |
No examples provided.
What is the io.github.agntcy/dir-mcp server?
io.github.agntcy/dir-mcp is listed in the public MCP registry as io.github.agntcy/dir-mcp. MCP server for working with OASF agent records in the Agntcy Directory. This page covers its container image (ghcr.io/agntcy/dir-mcp:1.3.4).
Is the io.github.agntcy/dir-mcp server safe to use?
io.github.agntcy/dir-mcp scores 54 out of 100 on VerifyMCP. 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.agntcy/dir-mcp server expose?
io.github.agntcy/dir-mcp exposes 12 tools: agntcy_dir_pull_record, agntcy_dir_push_record, agntcy_dir_search_local, agntcy_dir_verify_name, agntcy_dir_verify_record, and 7 more. Their descriptions and schemas cost roughly 2,493 tokens of context every time the server is loaded.
Is the io.github.agntcy/dir-mcp server still maintained?
io.github.agntcy/dir-mcp 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.agntcy/dir-mcp server under?
io.github.agntcy/dir-mcp 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.