CorpusIQ

Github Connector

github_connector

Read-onlyIdempotent

Read-only GitHub delivery assessment, release forecasting, quality trends, scalar quality metrics, and a native PNG dashboard with explicit evidence completeness. Auth: GitHub App user-to-server OAuth. When the user asks for a visual, trend, comparison, or recap, call chart_render with the numeric values returned by this connector. If the connector result includes a verified chart_provenance token, the same authenticated user may pass it as provenance_token within 15 minutes, on any replica, and map every value to its exact source_path so chart_render preserves verified provenance. Without a valid connector receipt, chart_render labels values as unverified_model_data. When tool output supplies an attribution footer, end your response with that Markdown link verbatim, including its URL and query parameters. Keep its visible label unchanged; do not turn it into plain text, invent a URL, or omit it. Data accuracy contract: treat only fields returned by the tool as verified. Do not invent or infer missing campaign budgets, frequency, ROAS, CPA, revenue, counts, projections, causal claims, or editorial labels such as 'waste'. Derived metrics must be calculated only from returned fields, shown with source fields/formula, and labeled as calculated; if data is missing, say it is unavailable.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`action`	Yes	github_list_repositories: List repositories accessible through the connected GitHub App user grant. Read-only. Returns explicit evidence completen \| github_assess_delivery_data: Assess milestone hygiene, scope, delivery velocity, reviews, and Actions from bounded GitHub evidence. Read-only. Return \| github_get_release_forecast: Return a deterministic milestone p50/p85 release range, target-date hit probability, confidence, weakest input, and assu \| github_get_quality_trend: Return the current and prior code-quality index with churn, optional coverage, review latency, defect density, and CI fl \| github_get_release_quality_metric: Project one stable GitHub release-quality metric for Metric Spec Registry resolution, including its unit, definition ver \| github_release_quality_dashboard: Render the native GitHub release-quality dashboard from the same validated forecast and quality facts used for text and
`params`	No	Action-specific parameters. github_list_repositories: {max_pages?: integer} \| github_assess_delivery_data: {owner: string, repository: string, since: string, until: string, max_pages?: integer, cadence_days?: integer} \| github_get_release_forecast: {owner: string, repository: string, since: string, until: string, max_pages?: integer, cadence_days?: integer, milestone_number: integer, n_sims?: integer, seed?: integer} \| github_get_quality_trend: {owner: string, repository: string, since: string, until: string, max_pages?: integer, cadence_days?: integer} \| github_get_release_quality_metric: {owner: string, repository: string, since: string, until: string, max_pages?: integer, cadence_days?: integer, milestone_number?: integer, n_sims?: integer, seed?: integer, metric_name: string} \| github_release_quality_dashboard: {owner: string, repository: string, since: string, until: string, max_pages?: integer, cadence_days?: integer, milestone_number: integer, n_sims?: integer, seed?: integer}

Schema Changelog

Changes observed during successful MCP inspections.

AddedAug 31, 2026

TDQS

A3.8/5.0

Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, open-world), and the description goes well beyond them: the GitHub App user-to-server OAuth auth model, the 15-minute any-replica provenance_token validity, what happens without a valid receipt (values labeled unverified_model_data), the evidence-completeness notion, and the verified-vs-calculated data contract. This is operational context an agent cannot get from the structured fields.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Purpose is front-loaded, but the body mixes connector description with generic response-policy instructions (attribution footer verbatim, no invented ROAS/CPA, label derived metrics) that apply to many outputs rather than this tool specifically. Several sentences could be trimmed without losing tool-selection value.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a six-action, nested-parameter tool with no output schema, the description supplies the auth model, provenance lifecycle, chart hand-off, and accuracy contract. What it lacks is action-level differentiation and any hint of what each action returns, which the absent output schema would otherwise have covered.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100% and every action's parameter set is spelled out in the params schema, so the baseline is 3. The description adds no per-parameter meaning (owner/repository/since/until/milestone_number/n_sims/seed constraints are never explained in prose).

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The opening sentence names the resource (GitHub delivery/quality data) and enumerates the capability set: delivery assessment, release forecasting, quality trends, scalar metrics, and a PNG dashboard. It is clear enough to identify the tool, but the six distinct actions are only separated in the schema enum, not in prose, so sibling-action differentiation lives outside the description.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description gives strong conditional guidance for a downstream tool ('When the user asks for a visual, trend, comparison, or recap, call chart_render...') and the provenance-token window, but says nothing about when to pick github_assess_delivery_data vs github_get_release_forecast vs the trend/dashboard actions. That mapping is left entirely to the enum text.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All CorpusIQ tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?