Skip to main content
Glama
gregordadera

aicb-roslyn-mcp

by gregordadera
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Local

Find Implementations

find_implementations
Read-onlyIdempotent

List all types that implement a C# interface, including external interfaces, so you can find every implementer before changing an interface member.

Instructions

List the types that implement an interface, declared in the solution or external (IDisposable, IEquatable). The interface counterpart to get_type_hierarchy (class inheritance) and find_overrides (methods).

Use it before changing an interface member, to find every type that has to follow.

Returns items [{name, isAbstract, kind, isTestProject, namespace, declaration, via}], count, totalFound, truncated - at most 100 items, sorted by name. kind is class, struct, record or interface; isAbstract marks an abstract base ('FooBase : IFoo'); 'declaration' is a generic implementer's arity-qualified form ('PolicyWrap'); via:'back-edge' marks an item known only from the interface's own implementer list, via:'inherited' one that gets an external interface through a solution base class or interface.

A closed query ('IHandler') lists the types closing it with those arguments, via bases and generic interfaces too; typeArgumentFilter counts the arity-matching types (tests too) closing it otherwise (otherClosings) or only over their own type parameters (openClosings). An unreadable closing stays, marked closing:'unresolved'.

Test-project implementers are excluded by default; testImplementationsFiltered: N says how many (absent = none), so a short list is never silently short.

An empty answer carries a 'hint' when the name is not an interface (use get_type_hierarchy or find_overrides) or no indexed type carries it (a did-you-mean when one is close; a delegate counts as undeclared), and a 'generatedCodeNote' when a source generator that did not run may have added the interface. When a project's core references did not resolve, a leading 'note' marks the inventory as partial until restore or build, then refresh_session.

Read-only. interfaceName is the simple name, case-sensitive: a namespace-qualified name matches nothing. Two interfaces that share a simple name answer as one list.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
sessionIdYesThe session_id returned by analyze_solution. Also takes an absolute .sln/.slnx/.slnf path, analyzed on first use.
includeTestsNoInclude test-project implementers (default false - production focus).
interfaceNameYesThe interface's simple name, e.g. 'ICodeAnalyzer'. An arity suffix ('IConsumer`1' / 'IConsumer<T>', or 'IConsumer`0' for the non-generic namesake) filters to that arity; a bare name keeps the merged view of every arity. A concrete type argument ('IConsumer<OrderPlaced>') keeps only the types that close it with that argument.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv0.5.46514
    • changedInput schema / properties / interfaceName / description
      Previous value: -"The interface's simple name, e.g. 'ICodeAnalyzer'. An arity suffix ('IConsumer`1' / 'IConsumer<T>', or 'IConsumer`0' for the non-generic namesake) filters to that arity; a bare name keeps the merged view of every arity."New value: +"The interface's simple name, e.g. 'ICodeAnalyzer'. An arity suffix ('IConsumer`1' / 'IConsumer<T>', or 'IConsumer`0' for the non-generic namesake) filters to that arity; a bare name keeps the merged view of every arity. A concrete type argument ('IConsumer<OrderPlaced>') keeps only the types that close it with that argument."
  2. Changed1 schema field changedv0.5.46513
    • changedInput schema / properties / sessionId / description
      Previous value: -"The session_id returned by analyze_solution."New value: +"The session_id returned by analyze_solution. Also takes an absolute .sln/.slnx/.slnf path, analyzed on first use."
  3. First observed

TDQS

A4.8/5.0
Behavior5/5

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

Annotations only declare the safety profile (read-only, idempotent, non-destructive); the description goes well beyond them, disclosing the 100-item cap and name sort, the default exclusion of test implementers plus the testImplementationsFiltered counter ('so a short list is never silently short'), unresolved-closing marking, partial-inventory notes, generatedCodeNote, and hint behaviour. This is exactly the operational context annotations cannot carry.

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

Conciseness4/5

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

Front-loaded with the core purpose and the sibling routing before the edge-case detail, and each sentence carries information. It is dense to the point of being long for a 3-parameter tool, but there is little outright waste.

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

Completeness5/5

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

No output schema exists, so the description carries the return contract itself: field list {name, isAbstract, kind, isTestProject, namespace, declaration, via}, count/totalFound/truncated, and the meaning of kind and via values. Nothing an agent needs to interpret or trust the result appears missing.

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

Parameters4/5

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

Schema coverage is 100% and the schema already documents the arity suffix and concrete-type-argument forms, so the baseline is 3. The description nonetheless adds non-obvious semantics the schema omits: the name is case-sensitive, a namespace-qualified name matches nothing, and two interfaces sharing a simple name answer as one merged list.

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

Purpose5/5

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

Starts with a specific verb+resource: 'List the types that implement an interface.' It also positions itself against named siblings — 'the interface counterpart to get_type_hierarchy (class inheritance) and find_overrides (methods)' — so an agent can discriminate without opening any schema.

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

Usage Guidelines5/5

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

Gives an explicit trigger ('Use it before changing an interface member, to find every type that has to follow') and routes elsewhere when the query is wrong ('when the name is not an interface (use get_type_hierarchy or find_overrides)'). Both when-to-use and when-not-to-use are covered.

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

Deploy Server

Other Tools